Recent Publications at IGI


To get an abstract click on the title of a paper. This list is also available as BiBTeX file.

2014

[1]
G. M. Hoerzer, R. Legenstein, and Wolfgang Maass. Emergence of complex computational structures from chaotic neural networks through reward-modulated Hebbian learning. Cerebral Cortex, 24:677-690, 2014. (PDF, 1505 KB). (Supplementary material PDF)

[2]
G. Indiveri, B. Linares-Barranco, R. Legenstein, G. Deligeorgis, and T. Prodromakis. Integration of nanoscale memristor synapses in neuromorphic computing architectures. Nanotechnology, 24:384010, 2014. (PDF).

[3]
D. Kappel, B. Nessler, and W. Maass. STDP installs in winner-take-all circuits an online approximation to hidden Markov model learning. PLOS Computational Biology, 10(3):e1003511, 2014. (Journal link to the PDF)

[4]
R. Legenstein and W. Maass. Ensembles of spiking neurons with noise support optimal probabilistic inference in a dynamically changing environment. PLOS Computational Biology, 2014. in press. (PDF, 2384 KB). (Supplementary material PDF)

[5]
W. Maass. Noise as a resource for computation and learning in networks of spiking neurons. Special Issue of the Proc. of the IEEE on "Engineering Intelligent Electronic Systems based on Computational Neuroscience", 102(5):860-880, 2014. (PDF, 1798 KB).

2013

[1]
W. Aigner, F. Aurenhammer, and B. Jüttler. On triangulation axes of polygons. Information Processing Letters, 2013. to appear. .

[2]
F. Aurenhammer, R. Klein, and D.T. Lee. Voronoi Diagrams and Delaunay Triangulations. World Scientific Publishing Company, Singapore, 2013.

[3]
F. Aurenhammer and G. Paulini. On shape Delaunay tessellations. Information Processing Letters, 2013. submitted. .

[4]
F. Aurenhammer and G. Walzl. Structure and computation of straight skeletons in 3-space. In Proc. 24th International Symposium on Algorithms and Computation ISAAC'13, Hong Kong, 2013. to appear.

[5]
F. Aurenhammer and G. Walzl. Three-dimensional straight skeletons from bisector graphs. In Proc. 5th International Conference on Analytic Number Theory and Spatial Tessellations, Kiev, Ukraine, 2013. to appear. .

[6]
S. Habenschuss, Z. Jonke, and W. Maass. Stochastic computations in cortical microcircuit models. PLOS Computational Biology, 9(11):e1003311, 2013. (PDF). (Additional technical information PDF)

[7]
S. Habenschuss, H. Puhr, and W. Maass. Emergence of optimal decoding of population codes through STDP. Neural Computation, 25(6):1371-1407, 2013. (PDF, 1105 KB).

[8]
M. Kapl, F. Aurenhammer, and B. Jüttler. Voronoi diagrams from distance graphs. In Proc. 29th European Workshop on Computational Geometry EuroCG 2013, pages 185-188, Braunschweig, Germany, 2013. .

[9]
M. Kapl, F. Aurenhammer, and B. Jüttler. Voronoi diagrams from (possibly disconnected) embeddings. In Proc. International Symposium on Voronoi Diagrams ISVD 2013, IEEE Computer Society, pages 47-50, St. Petersburg, Russia, 2013. .

[10]
M. Kapl, F. Aurenhammer, and B. Jüttler. Using scaled embedded distances to generate metrics for R2. In Proc. 14th IMA Conference on Mathematics of Surfaces, Birmingham, England, 2013. to be presented. .

[11]
S. Klampfl and W. Maass. Emergence of dynamic memory traces in cortical microcircuit models through STDP. The Journal of Neuroscience, 33(28):11515-11529, 2013. (PDF, 3984 KB).

[12]
B. Nessler, M. Pfeiffer, L. Buesing, and W. Maass. Bayesian computation emerges in generic cortical microcircuits through spike-timing-dependent plasticity. PLOS Computational Biology, 9(4):e1003037, 2013. (Journal link to the PDF)

[13]
E. A. Rueckert, G. Neumann, M. Toussaint, and W. Maass. Learned graphical models for probabilistic planning provide a new class of movement primitives. Frontiers in Computational Neuroscience, 6:1-20, 2013. doi:10.3389/fncom.2012.00097. (PDF, 1621 KB). (Journal link to the PDF)

2012

[1]
O. Aichholzer, F. Aurenhammer, E.D. Demaine, F. Hurtado, P. Ramos, and J. Urrutia. On k-convex polygons. Computational Geometry: Theory and Applications, 45:73-87, 2012. .

[2]
W. Aigner, F. Aurenhammer, and B. Jüttler. On triangulation axes of polygons. In Proc. 28th European Workshop on Computational Geometry EuroCG '2012, pages 125-128, Assisi, Italy, 2012. .

[3]
F. Aurenhammer and B. Jüttler. On computing the convex hull of (piecewise) curved objects. Mathematics in Computer Science, 6(3):261-266, 2012. .

[4]
S. Habenschuss, J. Bill, and B. Nessler. Homeostatic plasticity in bayesian spiking networks as expectation maximization with posterior constraints. In Advances in Neural Information Processing Systems, volume 25, pages 782-790, 2012.

[5]
H. Hauser, A. J. Ijspeert, R. M. Füchslin, R. Pfeifer, and W. Maass. The role of feedback in morphological computation with compliant bodies. Biological Cybernetics, published 06 Sept 2012. doi: 10.1007/s00422-012-0516-4. (PDF, 1573 KB). (Journal link to the PDF)

[6]
S. Klampfl, S. V. David, P. Yin, S. A. Shamma, and W. Maass. A quantitative analysis of information about past and present stimuli encoded by spikes of A1 neurons. Journal of Neurophysiology, 108:1366-1380, 2012. (PDF, 1045 KB). (Journal link to the abstract PDF)

[7]
B. Nessler, M. Pfeiffer, Lars Buesing, and W. Maass. Bayesian computation emerges in generic cortical microcircuits through spike-timing-dependent plasticity. submitted for publication, 2012.

[8]
M. Pfeiffer, M. Hartbauer, A. B. Lang, W. Maass, and H. Römer. Probing real sensory worlds of receivers with unsupervised clustering. PLoS ONE, 7(6):e37354. doi:10.1371, 2012. (PDF, 5928 KB). (Journal link to the PDF)

[9]
D. Probst, W. Maass, H. Markram, and M. O. Gewaltig. Liquid computing in a simplified model of cortical layer IV: Learning to balance a ball. In Proceedings of the 22nd International Conference on Artificial Neural Networks and Machine Learning -- ICANN 2012, Alessandro E.P. Villa, Wlodzislaw Duch, Peter Erdi, Francesco Masulli, and Günther Palm, editors, volume 7552 of Lecture Notes in Computer Science, pages 209-216. Springer, 2012. (PDF, 451 KB). (Journal link to the PDF)

[10]
T. Schiffer, F. Aurenhammer, and M. Demuth. Computing convex quadrangulations. Discrete Applied Mathematics, 160:648-656, 2012. .

2011

[1]
O. Aichholzer, W. Aigner, F. Aurenhammer, K. Cech Dobiasova, B. Jüttler, and G. Rote. Triangulations with circular arcs. In Proc. 19th Int. Symposium on Graph Drawing, Springer LNCS, volume 7034, pages 296-307, Eindhoven, Netherlands, 2011. .

[2]
O. Aichholzer, W. Aigner, F. Aurenhammer, and B. Jüttler. Exact medial axis computation for triangulated solids with respect to piecewise linear metrics. In Proc. Int. Conf. Curves and Surfaces, Springer LNCS, volume 6920, pages 1-27, Avignon, France, 2011. .

[3]
O. Aichholzer, F. Aurenhammer, T. Hackl, B. Juettler, M. Oberneder, and Z. Sir. Computational and structural advantages of circular boundary representation. Int'l Journal of Computational Geometry & Applications, 21:47-69, 2011. .

[4]
L. Büsing, J. Bill, B. Nessler, and W. Maass. Neural dynamics as sampling: A model for stochastic computation in recurrent networks of spiking neurons. PLoS Computational Biology, 7(11):e1002211, 2011. (Journal link to the PDF)

[5]
S. Habenschuss, H. Purr, and W. Maass. Emergence of optimal decoding of population codes through STDP. in preparation, 2011.

[6]
H. Hauser, A. J. Ijspeert, R. M. Füchslin, R. Pfeifer, and W. Maass. Towards a theoretical foundation for morphological computation with compliant bodies. Biological Cybernetics, 105(5-6):355-370, 2011. (PDF, 1649 KB). (Journal link to the PDF)

[7]
H. Hauser, G. Neumann, A. J. Ijspeert, and W. Maass. Biologically inspired kinematic synergies enable linear balance control of a humanoid robot. Biological Cybernetics, 104(4-5):235-249, 2011. (PDF, 1581 KB). (Journal link to the PDF)

[8]
R. Legenstein and W. Maass. Branch-specific plasticity enables self-organization of nonlinear computation in single neurons. The Journal of Neuroscience, 31(30):10787-10802, 2011. (PDF). (Commentary by R. P. Costa and P. J. Sjöström in Frontiers in Synaptic Neuroscience PDF)

[9]
D. Pecevski, L. Büsing, and W. Maass. Networks of spiking neurons are able to carry out probabilistic inference in general graphical models through their inherent stochastic dynamics. Technical report, Graz University of Technology, 2011.

[10]
D. Pecevski, L. Büsing, and W. Maass. Probabilistic inference in general graphical models through sampling in stochastic networks of spiking neurons. PLoS Computational Biology, 7(12):e1002294, 2011. (Journal link to the PDF)

[11]
M. J. Rasch, K. Schuch, N. K. Logothetis, and W. Maass. Statistical comparision of spike responses to natural stimuli in monkey area V1 with simulated responses of a detailed laminar network model for a patch of V1. Journal of Neurophysiology, 105:757-778, 2011. (PDF, 1929 KB). (Commentary by W.S. Anderson and B. Kreiman in Current Biology 2011 PDF)

2010

[1]
O. Aichholzer, W. Aigner, F. Aurenhammer, K. Cech Dobiasova, B. Jüttler, and G. Rote. Arc triangulations. In Proc. 26th European Workshop on Computational Geometry EuroCG '2010, pages 17-20, Dortmund, Germany, 2010. .

[2]
O. Aichholzer, W. Aigner, F. Aurenhammer, T. Hackl, B. Jüttler, E. Pilgerstorfer, and M. Rabl. Divide-and conquer for Voronoi diagrams revisited. Computational Geometry: Theory and Applications, 43:688-699, 2010. .

[3]
O. Aichholzer, F. Aurenhammer, T. Hackl, C. Huemer, A. Pilz, and B. Vogtenhuber. 3-colorability of pseudo-triangulations. In Proc. 26th European Workshop on Computational Geometry EuroCG'10, pages 21-24, Dortmund, Germany, 2010. .

[4]
J. Bill, K. Schuch, D. Brüderle, J. Schemmel, W. Maass, and K. Meier. Compensating inhomogeneities of neuromorphic VLSI devices via short-term synaptic plasticity. Frontiers in Computational Neuroscience, 4:1-14, 2010. doi:10.3389/fncom.2010.00129. (PDF, 2131 KB). (Journal link to the PDF)

[5]
L. Buesing and W. Maass. A spiking neuron as information bottleneck. Neural Computation, 22:1961-1992, 2010. (PDF, 706 KB).

[6]
L. Buesing, B. Schrauwen, and R. Legenstein. Connectivity, dynamics, and memory in reservoir computing with binary and analog neurons. Neural Computation, 22(5):1272-1311, 2010. (PDF, 1094 KB).

[7]
M. Demuth, F. Aurenhammer, and A. Pinz. Straight skeletons for binary shapes. In 3rd Workshop on non-rigid shape analysis and deformable image alignment (NORDIA'10), San Francisco, USA, 2010. .

[8]
M. Jahrer, A. Töscher, and R. Legenstein. Combining predictions for accurate recommender systems. In KDD '10: Proceedings of the 16th ACM SIGKDD international conference on Knowledge discovery and data mining, pages 693-702, New York, NY, USA, 2010. ACM. (PDF, 362 KB).

[9]
S. Klampfl and W. Maass. Replacing supervised classification learning by Slow Feature Analysis in spiking neural networks. In Proc. of NIPS 2009: Advances in Neural Information Processing Systems, volume 22, pages 988-996. MIT Press, 2010. (PDF, 1656 KB).

[10]
S. Klampfl and W. Maass. A theoretical basis for emergent pattern discrimination in neural systems through slow feature extraction. Neural Computation, 22(12):2979-3035, 2010. Epub 2010 Sep 21. (PDF, 1080 KB).

[11]
R. Legenstein, S. A. Chase, A. B. Schwartz, and W. Maass. Functional network reorganization in motor cortex can be explained by reward-modulated Hebbian learning. In Proc. of NIPS 2009: Advances in Neural Information Processing Systems, D. Koller, D. Schuurmans, Y. Bengio, and L. Bottou, editors, volume 22, pages 1105-1113. MIT Press, 2010. (PDF, 246 KB).

[12]
R. Legenstein, S. M. Chase, A. B. Schwartz, and W. Maass. A reward-modulated Hebbian learning rule can explain experimentally observed network reorganization in a brain control task. The Journal of Neuroscience, 30(25):8400-8410, 2010. (PDF, 718 KB).

[13]
R. Legenstein, N. Wilbert, and L. Wiskott. Reinforcement learning on slow features of high-dimensional input streams. PLoS Computational Biology, 6(8):e1000894, 2010. (PDF).

[14]
W. Maass. Liquid state machines: Motivation, theory, and applications. In Computability in Context: Computation and Logic in the Real World, B. Cooper and A. Sorbi, editors, pages 275-296. Imperial College Press, 2010. (PDF, 847 KB).

[15]
B. Nessler, M. Pfeiffer, and W. Maass. STDP enables spiking neurons to detect hidden causes of their inputs. In Proc. of NIPS 2009: Advances in Neural Information Processing Systems, volume 22, pages 1357-1365. MIT Press, 2010. (PDF, 203 KB).

[16]
M. Pfeiffer, B. Nessler, R. Douglas, and W. Maass. Reward-modulated Hebbian Learning of Decision Making. Neural Computation, 22:1399-1444, 2010. (PDF, 944 KB).

2009

[1]
O. Aichholzer, W. Aigner, F. Aurenhammer, T. Hackl, B. Jüttler, E. Pilgerstorfer, and M. Rabl. Divide-and conquer for Voronoi diagrams revisited. In Proc. 25th Ann. ACM Symp. Computational Geometry, pages 189-197, Aarhus, Denmark, 2009. .

[2]
O. Aichholzer, W. Aigner, F. Aurenhammer, T. Hackl, B. Jüttler, E. Pilgerstorfer, and M. Rabl. Divide-and conquer for Voronoi diagrams revisited. In Proc. 25th European Workshop on Computational Geometry EuroCG'09, pages 293-296, Brussels, Belgium, 2009. .

[3]
O. Aichholzer, W. Aigner, F. Aurenhammer, T. Hackl, B. Juettler, and M. Rabl. Medial axis computation for planar free-form shapes. Computer Aided Design, 41:339-349, 2009. Special Issue. .

[4]
O. Aichholzer, F. Aurenhammer, O. Devillers, T. Hackl, M. Teillaud, and B. Vogtenhuber. Lower and upper bounds on the number of empty cylinders and ellipsoids. In Proc. 25th European Workshop on Computational Geometry EuroCG'09, pages 139-141, Brussels, Belgium, 2009. .

[5]
O. Aichholzer, F. Aurenhammer, F. Hurtado, P.A. Ramos, and J. Urrutia. Two-convex polygons. In Proc. 25th European Workshop on Computational Geometry EuroCG'09, pages 117-120, Brussels, Belgium, 2009. .

[6]
O. Aichholzer, F. Aurenhammer, T. Hackl, and B. Speckmann. On minimum weight pseudo-triangulations. Computational Geometry: Theory and Applications, 42:627-631, 2009. .

[7]
O. Aichholzer, F. Aurenhammer, B. Kornberger, S. Plantinga, G. Rote, A. Sturm, and G. Vegter. Recovering structure from r-sampled objects. In Eurographics Symposium on Geometry Processing, Computer Graphics Forum, volume 28, pages 1349-1360, Berlin, Germany, 2009. Special Issue. .

[8]
B. Aronov, F. Aurenhammer, F. Hurtado, S. Langerman, D. Rappaport, S. Smorodinsky, and C. Seara. Small weak epsilon nets. Computational Geometry: Theory and Applications, 42:455-462, 2009. Special Issue. .

[9]
L. Buesing and W. Maass. A spiking neuron as information bottleneck. submitted for publication, 2009.

[10]
D. Buonomano and W. Maass. State-dependent computations: Spatiotemporal processing in cortical networks. Nature Reviews in Neuroscience, 10(2):113-125, 2009. (PDF, 665 KB).

[11]
S. Haeusler, K. Schuch, and W. Maass. Motif distribution, dynamical properties, and computational performance of two data-based cortical microcircuit templates. J. of Physiology (Paris), 103(1-2):73-87, 2009. (PDF, 844 KB).

[12]
G. Hoerzer. Methods for the analysis of uni-, bi- and multivariate data. Technical report, University of Technology, Institute for Theoretical Computer Sciences, 2009.

[13]
P. Joshi, G. Rainer, and W. Maass. Computational role of theta oscillations in delayed-decision tasks. in preparation, 2009.

[14]
S. Klampfl, S.V. David, P. Yin, S.A. Shamma, and W. Maass. Integration of stimulus history in information conveyed by neurons in primary auditory cortex in response to tone sequences. 39th Annual Conference of the Society for Neuroscience, Program 163.8, Poster T6, 2009.

[15]
S. Klampfl, R. Legenstein, and W. Maass. Spiking neurons can learn to solve information bottleneck problems and extract independent components. Neural Computation, 21(4):911-959, 2009. (PDF, 1088 KB).

[16]
S. Klampfl and W. Maass. A neuron can learn anytime classification of trajectories of network states without supervision. submitted for publication, Feb. 2009.

[17]
S. Klampfl and W. Maass. A theoretical basis for emergent pattern discrimination in neural systems through slow feature extraction. submitted, 2009.

[18]
R. Legenstein and W. Maass. An integrated learning rule for branch strength potentiation and STDP. 39th Annual Conference of the Society for Neuroscience, Program 895.20, Poster HH36, 2009.

[19]
S. Liebe, G. Hoerzer, N.K. Logothetis, W. Maass, and G. Rainer. Long range coupling between V4 and PF in theta band during visual short-term memory. 39th Annual Conference of the Society for Neuroscience, Program 652.20, Poster Y31, 2009.

[20]
B. Nessler, M. Pfeiffer, and W. Maass. Hebbian learning of Bayes optimal decisions. In Proc. of NIPS 2008: Advances in Neural Information Processing Systems, 21, 2009. MIT Press. (PDF, 224 KB).

[21]
G. Neumann, W. Maass, and J. Peters. Learning complex motions by sequencing simpler motion templates. In Proc. of the 26th Int. Conf. on Machine Learning (ICML 2009), Montreal, 2009. (PDF, 231 KB).

[22]
D. Nikolic, S. Haeusler, W. Singer, and W. Maass. Distributed fading memory for stimulus properties in the primary visual. submitted for publication, 2009.

[23]
D. Nikolic, S. Haeusler, W. Singer, and W. Maass. Distributed fading memory for stimulus properties in the primary visual cortex. PLoS Biology, 7(12):1-19, 2009. (PDF, 1301 KB).

[24]
D. Pecevski, T. Natschlaeger, and K. Schuch. PCSIM: A parallel simulation environment for neural circuits fully integrated with Python. Frontiers in Neuroinformatics, 3, 2009. doi:10.3389/neuro.11.011.2009. (PDF, 549 KB).

[25]
M. Pfeiffer, B. Nessler, W. Maass, and R. J. Douglas. Reward-modulated Hebbian learning of optimal decision making. Neural Computation, 2009.

[26]
M. Pfeiffer, B. Nessler, and W. Maass. STDP approximates expectation maximization in networks of spiking neurons with lateral inhibition. in preparation, 2009.

[27]
M. J. Rasch, K. Schuch, N. K. Logothetis, and W. Maass. Statistical characterization of the spike response to natural stimuli in monkey area V1 and in a detailed model for a patch of V1. submitted, 2009.

[28]
B. Schrauwen, L. Buesing, and R. Legenstein. On computational power and the order-chaos phase transition in reservoir computing. In Proc. of NIPS 2008, Advances in Neural Information Processing Systems, volume 21, pages 1425-1432. MIT Press, 2009. (PDF, 265 KB).

[29]
B. Schrauwen, L. Buesing, and R. Legenstein. Supplementary material to: On computational power and the order-chaos phase transition in reservoir computing. In Proc. of NIPS 2008, Advances in Neural Information Processing Systems, volume 21. MIT Press, 2009. in press. (PDF, 184 KB).

[30]
A. Steimer, W. Maass, and R. Douglas. Belief-propagation in networks of spiking neurons. Neural Computation, 21:2502-2523, 2009. (PDF, 651 KB).

2008

[1]
O. Aichholzer, F. Aurenhammer, P. Gonzalez-Nava, T. Hackl, C. Huemer, F. Hurtado, H. Krasser, S. Ray, and B. Vogtenhuber. Matching edges and faces in polygonal partitions. Computational Geometry: Theory and Applications, 39:134-141, 2008. .

[2]
O. Aichholzer, F. Aurenhammer, T. Hackl, B. Kornberger, S. Plantinga, G. Rote, A. Sturm, and G. Vegter. Seed polytopes for incremental approximation. In Proc. 24th European Workshop on Computational Geometry EuroCG '08, pages 13-16, Nancy, France, 2008. .

[3]
P. Auer, H. Burgsteiner, and W. Maass. A learning rule for very simple universal approximators consisting of a single layer of perceptrons. Neural Networks, 21(5):786-795, 2008. (PDF, 468 KB).

[4]
F. Aurenhammer, M. Demuth, and T. Schiffer. Computing convex quadrangulations. In Proc. 5th Ann. Int. Symp. Voronoi Diagrams in Science and Engineering, Voronoi's Impact on Modern Science, volume 4, pages 32-43, Kiev, Ukraine, 2008. .

[5]
F. Aurenhammer and Y.-F.Xu. Optimal triangulations. In Encyclopedia of Optimization, Second Edition, P.M.Pardalos C.A.Floudas, editor, pages 2757-2764. Springer, 2008. .

[6]
J. Bill. Self-stabilizing network architectures on a neuromorphic hardware system. Master's thesis, Universitaet Heidelberg, 2008.

[7]
L. Buesing and W. Maass. Simplified rules and theoretical analysis for information bottleneck optimization and PCA with spiking neurons. In Proc. of NIPS 2007, Advances in Neural Information Processing Systems, volume 20. MIT Press, 2008. (PDF, 394 KB).

[8]
C. Clopath, L. Ziegler, E. Vasilaki, L. Buesing, and W. Gerstner. Tag-trigger-consolidation: A model of early and late long-term-potentiation and depression. PLOS Computational Biology, 4(12):e1000248, 2008. (PDF).

[9]
S. Haeusler, K. Schuch, and W. Maass. Motif distribution and computational performance of two data-based cortical microcircuit templates. 38th Annual Conference of the Society for Neuroscience, Program 220.9, 2008.

[10]
G. Hoerzer. Extraction of information about the behavioral state of monkeys from neuronal recordings with methods from machine learning. Master's thesis, Graz University of Technology, Institute for Theoretical Computer Sciences, 2008.

[11]
P. Joshi and J. Triesch. A globally asymptotically stable plasticity rule for firing rate homeostasis. In Artificial Neural Networks -- ICANN 2008, 2008. .

[12]
P. Joshi and J. Triesch. Rules for information-maximization in spiking neurons using intrinsic plasticity. In Submitted for publication, 2008. .

[13]
R. Legenstein, S. A. Chase, A. B. Schwartz, and W. Maass. A model for learning effects in motor cortex that may facilitate the brain control of neuroprosthetic devices. 38th Annual Conference of the Society for Neuroscience, Program 517.6, 2008.

[14]
R. Legenstein and W. Maass. On the classification capability of sign-constrained perceptrons. Neural Computation, 20(1):288-309, 2008. (PDF, 671 KB).

[15]
R. Legenstein, D. Pecevski, and W. Maass. Theoretical analysis of learning with reward-modulated spike-timing-dependent plasticity. In Proc. of NIPS 2007, Advances in Neural Information Processing Systems, volume 20, pages 881-888. MIT Press, 2008. (PDF, 199 KB).

[16]
R. Legenstein, D. Pecevski, and W. Maass. A learning theory for reward-modulated spike-timing-dependent plasticity with application to biofeedback. PLoS Computational Biology, 4(10):e1000180, 2008. (Journal link to the PDF)

[17]
M. A. Montemurro, M. J. Rasch, Y. Murayam, N. K. Logothetis, and S. Panzeri. Phase-of-firing coding of natural visual stimuli in primary visual cortex. Current Biology, 18:375-380, 2008. (PDF, 944 KB).

[18]
M. Rasch. Analysis of neural signals: Interdependence, information coding, and relation to network models. PhD thesis, Graz University of Technology, Institute for Theoretical Computer Science, 2008.

[19]
M. J. Rasch, A. Gretton, Y. Murayama, W. Maass, and N. K. Logothetis. Inferring spike trains from local field potentials. Journal of Neurophysiology, 99:1461-1476, 2008. (PDF, 873 KB).

[20]
C. Savin, P. Joshi, and J. Triesch. Ica with spiking neurons. In Submitted for publication, 2008. .

[21]
Andreas Toescher, Michael Jahrer, and Robert Legenstein. Improved neighborhood-based algorithms for large-scale recommender systems. In KDD-Cup and Workshop. ACM, 2008. in press. (PDF, 121 KB).

2007

[1]
O. Aichholzer, F. Aurenhammer, and T. Hackl. Pre-triangulations and liftable complexes. Discrete & Computational Geometry, 38:701-725, 2007. .

[2]
O. Aichholzer, F. Aurenhammer, T. Hackl, and C. Huemer. Connecting colored point sets. Discrete Applied Mathematics, 155:271-278, 2007. .

[3]
O. Aichholzer, F. Aurenhammer, T. Hackl, B. Juettler, M. Oberneder, and Z. Sir. Computational and structural advantages of circular boundary representation. In Proc. 10th Int. Workshop on Algorithms and Data Structures, WADS'07, Springer LNCS 4619, pages 374-385, Halifax, Canada, 2007. .

[4]
O. Aichholzer, F. Aurenhammer, T. Hackl, B. Kornberger, M. Peternell, and H. Pottmann. Approximating boundary-triangulated objects with balls. In Proc. 23rd European Workshop on Computational Geometry, EWCG'07, pages 130-133, Graz, Austria, 2007. .

[5]
O. Aichholzer, F. Aurenhammer, T. Hackl, and B. Speckmann. On (pointed) minimum weight pseudo-triangulations. In Proc. 19th Canadian Conference on Computational Geometry CCCG '07, pages 209-212, Ottawa, Canada, 2007. .

[6]
O. Aichholzer, F. Aurenhammer, C. Huemer, and B. Vogtenhuber. Gray code enumeration of plane straight-line graphs. Graphs and Combinatorics, 23:467-479, 2007. .

[7]
F. Aurenhammer. Weighted skeletons and fixed-share decomposition. Computational Geometry: Theory and Applications, 40:93-101, 2007. .

[8]
F. Aurenhammer, M. Peternell, H. Pottmann, and J. Wallner. Voronoi diagrams for oriented spheres. In Proc. 4th Int. Symp. on Voronoi Diagrams in Science and Engineering, ISVD'07, pages 33-37, Pontypridd, UK, 2007. .

[9]
R. Brette and D. Pecevski. Simulation of networks of spiking neurons: a review of tools and strategies. J. Computer Neuroscience, 23(3):349-398, 2007.

[10]
R. Brette, M. Rudolph, T. Carnevale, M. Hines, D. Beeman, J. M. Bower, M. Diesmann, A. Morrison, P. H. Goodman, F. C. Harris, M. Zirpe, T. Natschlaeger, D. Pecevski, B. Ermentrout, M. Djurfeldt, A. Lansner, O. Rochel, T. Vieville, E. Muller, A. P. Davison, S. ElBoustani, and A. Destexhe. Simulation of networks of spiking neurons: A review of tools and strategies. J. of Computational Neuroscience, 23(3):349-398, 2007. (PDF, 5398 KB).

[11]
H. Burgsteiner, M. Kröll, A. Leopold, and G. Steinbauer. Movement prediction from real-world images using a liquid state machine. Applied Intelligence, 26(2):99--, 2007.

[12]
A. Gretton, K. M. Borgwardt, M. J. Rasch, B. Schölkopf, and A. J. Smola. A kernel method to comparing distributions. In Proceedings of the Twenty-Second AAAI Conference on Artificial Intelligence (AAAI-07), volume 22, pages 1637-1641. AAAI Press, Menlo Park, CA, USA, 2007.

[13]
S. Haeusler and W. Maass. A statistical analysis of information processing properties of lamina-specific cortical microcircuit models. Cerebral Cortex, 17(1):149-162, 2007. (PDF, 889 KB).

[14]
S. Haeusler, W. Singer, W. Maass, and D. Nikolic. Superposition of information in large ensembles of neurons in primary visual cortex. 37th Annual Conference of the Society for Neuroscience, Program 176.2, Poster II23, 2007.

[15]
H. Hauser, G. Neumann, A. J. Ijspeert, and W. Maass. Biologically inspired kinematic synergies provide a new paradigm for balance control of humanoid robots. In Proceedings of the IEEE-RAS 7th International Conference on Humanoid Robots (Humanoids 2007), 2007. Best Paper Award. http://planning.cs.cmu.edu/humanoids07/p/37.pdf. (PDF, 671 KB).

[16]
H. Jaeger, W. Maass, and J. Principe. Special issue on echo state networks and liquid state machines. Neural Networks, 20(3):287-289, 2007. (PDF, 128 KB).

[17]
P. Joshi. From memory based decisions to decision based movements: A model of interval discrimination followed by action selection. Neural Networks, 20:298-311, 2007. (PDF, 1592 KB).

[18]
P. Joshi. On the role of feedback in enhancing the computational power of generic neural microcircuits. PhD thesis, Graz University of Technology, 2007. (PDF, 2584 KB).

[19]
S. Klampfl, R. Legenstein, and W. Maass. Information bottleneck optimization and independent component extraction with spiking neurons. In Proc. of NIPS 2006, Advances in Neural Information Processing Systems, volume 19, pages 713-720. MIT Press, 2007. (PDF, 613 KB).

[20]
R. Legenstein and W. Maass. What makes a dynamical system computationally powerful?. In New Directions in Statistical Signal Processing: From Systems to Brains, S. Haykin, J. C. Principe, T.J. Sejnowski, and J.G. McWhirter, editors, pages 127-154. MIT Press, 2007. (PDF, 582 KB).

[21]
R. Legenstein and W. Maass. Edge of chaos and prediction of computational performance for neural circuit models. Neural Networks, 20(3):323-334, 2007. (PDF, 1480 KB).

[22]
W. Maass. Liquid computing. In Proceedings of the Conference CiE'07: COMPUTABILITY IN EUROPE 2007, Siena (Italy), Lecture Notes in Computer Science, pages 507-516. Springer (Berlin), 2007. (PDF, 547 KB).

[23]
W. Maass, P. Joshi, and E. D. Sontag. Computational aspects of feedback in neural circuits. PLoS Computational Biology, 3(1):e165, 2007. (Journal link to the PDF)

[24]
E. Muller, L. Buesing, J. Schemmel, and K. Meier. Spike-frequency adapting neural ensembles: Beyond mean adaptation and renewal theories. Neural Computation, 19(11), 2007.

[25]
G. Neumann, M. Pfeiffer, and W. Maass. Efficient continuous-time reinforcement learning with adaptive state graphs. In Proceedings of the 18th European Conference on Machine Learning (ECML) and the 11th European Conference on Principles and Practice of Knowledge Discovery in Databases (PKDD) 2007, Warsaw (Poland). Springer (Berlin), 2007. in press. (PDF, 366 KB).

[26]
D. Nikolic, S. Haeusler, W. Singer, and W. Maass. Temporal dynamics of information content carried by neurons in the primary visual cortex. In Proc. of NIPS 2006, Advances in Neural Information Processing Systems, volume 19, pages 1041-1048. MIT Press, 2007. (PDF, 176 KB).

[27]
D. Sussillo, T. Toyoizumi, and W. Maass. Self-tuning of neural circuits through short-term synaptic plasticity. Journal of Neurophysiology, 97:4079-4095, 2007. (PDF, 1504 KB).

2006

[1]
O. Aichholzer, F. Aurenhammer, and T. Hackl. Pre-triangulations and liftable complexes. In 22nd Ann. ACM Symp. Computational Geometry, pages 282-291, Sedona, Arizona, USA, 2006. .

[2]
O. Aichholzer, F. Aurenhammer, C. Huemer, and H. Krasser. Transforming spanning trees and pseudo-triangulations. Information Processing Letters, 97:19-22, 2006. .

[3]
O. Aichholzer, F. Aurenhammer, C. Huemer, and B. Vogtenhuber. Gray code enumeration of plane straight-line graphs. In Proc. 22nd European Workshop on Computational Geometry EuroCG '06, pages 71-74, Delphi, Greece, 2006. .

[4]
O. Aichholzer, F. Aurenhammer, and H. Krasser. On the crossing number of complete graphs. Computing, 76:165-176, 2006. .

[5]
F. Aurenhammer, R.L.S.Drysdale, and H. Krasser. Farthest line segment Voronoi diagrams. Information Processing Letters, 100:220-225, 2006. .

[6]
F. Aurenhammer and H. Krasser. Pseudo-simplicial complexes from maximal locally convex functions. Discrete & Computional Geometry, 35:201-221, 2006. .

[7]
M. Bachler. Bayesian and information theoretic methods for the selection and creation of high-level features applied to real-world object classification tasks. Technical report, Technische Universitaet Graz, 2006.

[8]
M. Bachler and W. Maass. A Bayesian Hebb rule for incremental learning of optimal inference in Bayesian networks. submitted for publication, 2006.

[9]
K. M. Borgwardt, A. Gretton, M. J. Rasch, H.-P. Kriegel, B. Schoelkopf, and A. J. Smola. Integrating structured biological data by kernel Maximum Mean Discrepancy. Bioinformatics, 22(14):349-e57, 2006.

[10]
Y. Fregnac, M. Blatow, J.-P. Changeux, J. de Felipe, A. Lansner, W. Maass, D. A. McCormick, C. M. Michel, H. Monyer, E. Szathmary, and R. Yuste. UPs and DOWNs in cortical computation. In The Interface between Neurons and Global Brain Function, S. Grillner and A. M. Graybiel, editors, Dahlem Workshop Report 93, pages 393-433. MIT Press, 2006. (PDF, 606 KB).

[11]
A. Gretton, K. M. Borgwardt, M. J. Rasch, and A. J. Smola. Data-content based schema matching via Maximum Mean Discrepancy. submitted for publication, 2006.

[12]
A. Gretton, K. M. Borgwardt, M. J. Rasch, B. Schölkopf, and A. J. Smola. A kernel method for the two-sample-problem. In Proceedings of the 2006 Conference Advances in Neural Information Processing Systems 19, volume 20, pages 513-520. MIT Press, 2006.

[13]
S. Haeusler and W. Maass. Computational impact of laminar structure and small world properties of cortical microcircuit models. submitted for publication, 2006.

[14]
M. Hoefler and M. Bachler. A software framework for adaptive biologically inspired image classification. Technical report, Technische Universitaet Graz, 2006.

[15]
P. Joshi. Modeling working memory and decision making using generic neural microcircuits. In Artificial Neural Networks -- ICANN 2006, Stefanos Kollias, Andreas Stafylopatis, Wlodzislaw Duch, and Erkki Oja, editors, volume 4131 of Lecture Notes in Computer Science, pages 515-524. Springer, 2006. (PDF, 568 KB).

[16]
A. Kaske and W. Maass. A model for the interaction of oscillations and pattern generation with real-time computing in generic neural microcircuit models. Neural Networks, 19(5):600-609, 2006. (PDF, 832 KB).

[17]
S. Klampfl. Extracting statistically independent components with a generalized BCM rule for spiking neurons. Master's thesis, Graz University of Technology, 2006.

[18]
R. Legenstein and W. Maass. A criterion for the convergence of learning with spike timing dependent plasticity. In Advances in Neural Information Processing Systems, Y. Weiss, B. Schoelkopf, and J. Platt, editors, volume 18, pages 763-770. MIT Press, 2006. (PDF, 194 KB).

[19]
W. Maass. Book review of "Imitation of life: how biology is inspiring computing" by Nancy Forbes. Pattern Analysis and Applications, 8(4):390-391, 2006. Springer (London). (PDF, 105 KB).

[20]
W. Maass, P. Joshi, and E. D. Sontag. Principles of real-time computing with feedback applied to cortical microcircuit models. In Advances in Neural Information Processing Systems, Y. Weiss, B. Schoelkopf, and J. Platt, editors, volume 18, pages 835-842. MIT Press, 2006. (PDF, 806 KB).

[21]
W. Maass and H. Markram. Theory of the computational function of microcircuit dynamics. In The Interface between Neurons and Global Brain Function, S. Grillner and A. M. Graybiel, editors, Dahlem Workshop Report 93, pages 371-390. MIT Press, 2006. (PDF, 402 KB).

[22]
D. Nikolic, S. Haeusler, W. Singer, and W. Maass. Temporal dynamics of informational contents carried by neurons in the primary visual cortex. submitted for publication, 2006.

[23]
M. Pfeiffer, A. R. Saffari A. A., and A. Juffinger. Predicting text relevance from sequential reading behavior. In Proceedings of the NIPS 2005 Workshop on Machine Learning for Implicit Feedback and User Modeling, K. Puolamaeki and S. Kaski, editors, pages 25-30, Otaniemi, Finland, May 2006. Helsinki University of Technology. (PDF, 51 KB).

[24]
M. Rasch, A. Gretton, Y. Murayama, W. Maass, and N. Logothetis. Interaction of local field potential and spiking activity in area V1. Technical report, Technische Universitaet Graz and MPI Tuebingen, 2006.

[25]
M. Rasch, S. Haeusler, Z. Kisvarday, W. Maass, and N. Logothetis. Comparison of a detailed model for area V1 with simultaneous recordings from LGN and V1. Technical report, Technische Universitaet Graz and MPI Tuebingen, 2006.

[26]
M. Rasch and Z. Kisvarday. Design of stimuli for investigating spatial integration of information in optical recordings. Technical report, Technische Universitaet Graz and University of Debrecen, 2006.

[27]
K. Uchizawa, R. Douglas, and W. Maass. On the computational power of threshold circuits with sparse activity. Neural Computation, 18(12):2994-3008, 2006. (PDF, 111 KB).

[28]
K. Uchizawa, R. Douglas, and W. Maass. Energy complexity and entropy of threshold circuits. In Proceedings of the 33rd International Colloquium on Automata, Languages and Programming, ICALP (1) 2006, Venice, Italy, July 10-14, 2006, Part I, M. Bugliesi, B. Preneel, V. Sassone, and I. Wegener, editors, volume 4051 of Lecture Notes in Computer Science, pages 631-642. Springer, 2006. (PDF, 1790 KB).

[29]
M. Winter, H. Bischof, M. Rasch, and W. Maass. Results and open problems regarding the role of local feature descriptors for image classification in computer vision, and image representations in primary visual cortex. Technical report, Technische Universitaet Graz, 2006.

2005

[1]
O. Aichholzer, F. Aurenhammer, P. Gonzalez-Nava, T. Hackl, C. Huemer, F. Hurtado, H. Krasser, S. Ray, and B. Vogtenhuber. Matching edges and faces in polygonal partitions. In Proc. 17th Canadian Conference on Computational Geometry CCCG '05, pages 123-126, Windsor, Ontario, 2005. .

[2]
O. Aichholzer, F. Aurenhammer, C. Huemer, and H. Krasser. Transforming spanning trees and pseudo-triangulations. In Proc. 21st European Workshop on Computational Geometry EuroCG '05, pages 81-84, Eindhoven, The Netherlands, 2005. .

[3]
B. Aronov, F. Aurenhammer, F. Hurtado, S. Langerman, D. Rappaport, S. Smorodinsky, and C. Seara. Small weak epsilon nets. In Proc. 17th Canadian Conference on Computational Geometry CCCG '05, pages 51-54, Windsor, Ontario, 2005. .

[4]
F. Aurenhammer. Pre-triangulations: A generalization of Delaunay triangulations and flips. In 2nd Intern. Symp. on Voronoi Diagrams in Science and Engineering, page 235, Hanyang University, Seoul, Korea, 2005. (plenar talk).

[5]
F. Aurenhammer and H. Krasser. Pseudo-tetrahedral complexes. In Proc. 21st European Workshop on Computational Geometry EuroCG '05, pages 85-88, Eindhoven, The Netherlands, 2005. .

[6]
M. Bachler. Task dependent feature optimization in machine learning. Master's thesis, Technische Universitaet Graz, 2005.

[7]
A. Gretton, R. Herbrich, A. Smola, O. Bousquet, and B. Schölkopf. Kernel methods for measuring independence. Journal of Machine Learning Research, 6:2075-2129, 2005.

[8]
P. Joshi and W. Maass. Movement generation with circuits of spiking neurons. Neural Computation, 17(8):1715-1738, 2005. (PDF, 1156 KB).

[9]
A. Kaske and N. Bertschinger. Travelling wave patterns in a model of the spinal pattern generator using spiking neurons. Biol. Cybern., 92(3):206-218, 2005.

[10]
R. Legenstein, C. Naeger, and W. Maass. What can a neuron learn with spike-timing-dependent plasticity?. Neural Computation, 17(11):2337-2382, 2005. (PDF, 549 KB).

[11]
R. A. Legenstein and W. Maass. Wire length as a circuit complexity measure. Journal of Computer and System Sciences, 70:53-72, 2005. (PDF, 372 KB).

[12]
W. Maass, R. Legenstein, and N. Bertschinger. Methods for estimating the computational power and generalization capability of neural microcircuits. In Advances in Neural Information Processing Systems, L. K. Saul, Y. Weiss, and L. Bottou, editors, volume 17, pages 865-872. MIT Press, 2005. (PDF, 196 KB).

[13]
T. Natschlaeger, N. Bertschinger, and R. Legenstein. At the edge of chaos: Real-time computations and self-organized criticality in recurrent neural networks. In Advances in Neural Information Processing Systems 17, Lawrence K. Saul, Yair Weiss, and Léon Bottou, editors, pages 145-152. MIT Press, Cambridge, MA, 2005. (PDF, 706 KB).

[14]
T. Natschlaeger and W. Maass. Dynamics of information and emergent computation in generic neural microcircuit models. Neural Networks, 18(10):1301-1308, 2005. (PDF, 273 KB).

2004

[1]
O. Aichholzer, F. Aurenhammer, H. Krasser, and B. Speckmann. Convexity minimizes pseudo-triangulations. Computational Geometry: Theory and Applications, 28:3-10, 2004. .

[2]
O. Aichholzer, F. Aurenhammer, and B. Palop. Quickest paths, straight skeletons, and the city Voronoi diagram. Discrete & Computational Geometry, 31(1):17-35, 2004. .

[3]
O. Aichholzer, C. Huemer, and H. Krasser. Triangulations without pointed spanning trees - extended abstract. In Proc. 20th European Workshop on Computational Geometry EWCG '04, pages 221-224, Sevilla, Spain, 2004. .

[4]
O. Aichholzer, F. Hurtado, and M. Noy. A lower bound on the number of triangulations of planar point sets. Computational Geometry: Theory and Applications, 29(2):135-145, 2004. . . See also the Counting Triangulations - Olympics.

[5]
O. Aichholzer, D. Orden, F. Santos, and B. Speckmann. On the number of pseudo-triangulations of certain point sets. In Proc. 20th European Workshop on Computational Geometry EWCG '04, pages 119-122, Sevilla, Spain, 2004. .

[6]
O. Aichholzer and K. Reinhardt. A quadratic distance bound on sliding between crossing-free spanning trees - extended abstract. In Proc. 20th European Workshop on Computational Geometry EWCG '04, pages 13-16, Sevilla, Spain, 2004. .

[7]
N. Bertschinger and T. Natschlaeger. Real-time computation at the edge of chaos in recurrent neural networks. Neural Computation, 16(7):1413-1436, 2004. (PDF, 476 KB).

[8]
Mathaeus Dejori, Anton Schwaighofer, Volker Tresp, and Martin Stetter. Mining functional modules in genetic networks with decomposable graphical models. OMICS A Journal of Integrative Biology, 2004. Accepted for publication.

[9]
P. Joshi and W. Maass. Movement generation and control with generic neural microcircuits. In Biologically Inspired Approaches to Advanced Information Technology. First International Workshop, BioADIT 2004, Lausanne, Switzerland, January 2004, Revised Selected Papers, A. J. Ijspeert, M. Murata, and N. Wakamiya, editors, volume 3141 of Lecture Notes in Computer Science, pages 258-273. Springer Verlag, 2004. (PDF, 596 KB).

[10]
R. Legenstein and W. Maass. Additional material to the paper: What can a neuron learn with spike-timing-dependent plasticity? Technical report, Institute for Theoretical Computer Science, Graz University of Technology, 2004. . (PDF)

[11]
W. Maass and H. Markram. On the computational power of circuits of spiking neurons. Journal of Computer and System Sciences, 69(4):593-616, 2004. (PDF, 355 KB).

[12]
W. Maass, T. Natschlaeger, and H. Markram. Fading memory and kernel properties of generic cortical microcircuit models. Journal of Physiology -- Paris, 98(4-6):315-330, 2004. (PDF, 576 KB).

[13]
W. Maass, T. Natschlaeger, and H. Markram. Computational models for generic cortical microcircuits. In Computational Neuroscience: A Comprehensive Approach, J. Feng, editor, chapter 18, pages 575-605. Chapman & Hall/CRC, Boca Raton, 2004. (PDF, 863 KB).

[14]
O. Melamed, W. Gerstner, W. Maass, M. Tsodyks, and H. Markram. Coding and learning of behavioral sequences. Trends in Neurosciences, 27(1):11-14, 2004. (PDF, 105 KB).

[15]
T. Natschlaeger and W. Maass. Information dynamics and emergent computation in recurrent circuits of spiking neurons. In Proc. of NIPS 2003, Advances in Neural Information Processing Systems, S. Thrun, L. Saul, and B. Schoelkopf, editors, volume 16, pages 1255-1262, Cambridge, 2004. MIT Press. (PDF, 180 KB).

[16]
Anton Schwaighofer, Marian Grigoras, Volker Tresp, and Clemens Hoffmann. GPPS: A Gaussian process positioning system for cellular networks. In Advances in Neural Information Processing Systems 16, Sebastian Thrun, Lawrence Saul, and Bernhard Schoelkopf, editors, 2004.

[17]
Kai Yu, Anton Schwaighofer, Volker Tresp, Xiaowei Xu, and Hans-Peter Kriegel. Probabilistic memory based collaborative filtering: Learning individual and social preferences. IEEE Transactions on Knowledge and Data Engineering (Special issue on mining and searching the web), 16(1):56-69, 2004.

2003

[1]
O. Aichholzer, F. Aurenhammer, P. Brass, and H. Krasser. Pseudo-triangulations from surfaces and a novel type of edge flip. SIAM Journal on Computing, 32:1621-1653, 2003. .

[2]
O. Aichholzer, F. Aurenhammer, P. Brass, and H. Krasser. Spatial embedding of pseudo-triangulations. In Proc. 19th Ann. ACM Symp. Computational Geometry, pages 144-153, San Diego, California, USA, 2003. .

[3]
O. Aichholzer, F. Aurenhammer, F. Hurtado, and H. Krasser. Towards compatible triangulations. Theoretical Computer Science, 296:3-13, 2003. Special Issue. .

[4]
O. Aichholzer, F. Aurenhammer, and H. Krasser. Adapting (pseudo)-triangulations with a near-linear number of edge flips. In Lecture Notes in Computer Science 2748, Proc. 8th International Workshop on Algorithms and Data Structures (WADS), volume 2748, pages 12-24, 2003. .

[5]
O. Aichholzer, D. Bremner, E.D. Demaine, F. Hurtado, E. Kranakis, H. Krasser, S. Ramaswami, S. Sethia, and J. Urrutia. Geometric games on triangulations. In Proc. 19th European Workshop on Computationl Geometry CG '03 Bonn, pages 89-92, Bonn, Germany, 2003. .

[6]
O. Aichholzer, D. Bremner, E.D. Demaine, F. Hurtado, E. Kranakis, H. Krasser, S. Ramaswami, S. Sethia, and J. Urrutia. Playing with triangulations. In Lecture Notes in Computer Science 2866, Japanese Conference, JCDCG 2002, pages 22-37, 2003. .

[7]
O. Aichholzer, D. Bremner, E.D. Demaine, D. Meijer, V. Sacristán, and M. Soss. Long proteins with unique optimal foldings in the h-p model. Computational Geometry: Theory and Applications, 25:139-159, 2003. .

[8]
O. Aichholzer, M. Hoffmann, B. Speckmann, and C. D. Tóth. Degree bounds for constrained pseudo-triangulations. In Proc. 15th Annual Canadian Conference on Computational Geometry CCCG 2003, pages 155-158, Halifax, Nova Scotia, Canada, 2003. .

[9]
O. Aichholzer, D. Orden, F. Santos, and B. Speckmann. On the number of pseudo-triangulations of certain point sets. In Proc. 15th Annual Canadian Conference on Computational Geometry CCCG 2003, pages 141-144, Halifax, Nova Scotia, Canada, 2003. .

[10]
O. Aichholzer, G. Rote, B. Speckmann, and I. Streinu. The zigzag path of a pseudo-triangulation. In Lecture Notes in Computer Science 2748, Proc. 8th International Workshop on Algorithms and Data Structures (WADS), volume 2748, pages 377-389, 2003. .

[11]
F. Aurenhammer. Pseudo-simplices and their derivation. In Voronoi Conference on Analytic Number Theory and Spatial Tesselations, page 11, Inst. Math. National Academy of Sciences, Kiev, Ukraine, 2003.

[12]
Peter L. Bartlett and W. Maass. Vapnik-Chervonenkis dimension of neural nets. In The Handbook of Brain Theory and Neural Networks, M. A. Arbib, editor, pages 1188-1192. MIT Press (Cambridge), 2nd edition, 2003. (PDF, 134 KB).

[13]
S. Haeusler, H. Markram, and W. Maass. Perspectives of the high-dimensional dynamics of neural microcircuits from the point of view of low-dimensional readouts. Complexity (Special Issue on Complex Adaptive Systems), 8(4):39-50, 2003. (PDF, 183 KB).

[14]
H. Krasser. Order Types of Point Sets in the Plane. PhD thesis, Institute for Theoretical Computer Science, Graz University of Technology, Austria, October 2003. .

[15]
R. Legenstein, H. Markram, and W. Maass. Input prediction and autonomous movement analysis in recurrent circuits of spiking neurons. Reviews in the Neurosciences (Special Issue on Neuroinformatics of Neural and Artificial Computation), 14(1-2):5-19, 2003. (PDF, 179 KB).

[16]
W. Maass. Computation with spiking neurons. In The Handbook of Brain Theory and Neural Networks, M. A. Arbib, editor, pages 1080-1083. MIT Press (Cambridge), 2nd edition, 2003. (Gzipped PostScript, 17 p., 72 KB). (PDF, 170 KB).

[17]
W. Maass and H. Markram. Temporal integration in recurrent microcircuits. In The Handbook of Brain Theory and Neural Networks, M. A. Arbib, editor, pages 1159-1163. MIT Press (Cambridge), 2nd edition, 2003. (PDF, 249 KB).

[18]
W. Maass, T. Natschlaeger, and H. Markram. A model for real-time computation in generic neural microcircuits. In Proc. of NIPS 2002, Advances in Neural Information Processing Systems, S. Becker, S. Thrun, and K. Obermayer, editors, volume 15, pages 229-236. MIT Press, 2003. (PDF, 254 KB).

[19]
T. Natschlaeger, H. Markram, and W. Maass. Computer models and analysis tools for neural microcircuits. In Neuroscience Databases. A Practical Guide, R. Koetter, editor, chapter 9, pages 121-136. Kluwer Academic Publishers (Boston), 2003. (PDF, 230 KB).

[20]
Anton Schwaighofer. Kernel Systems for Regression and Graphical Modelling. PhD thesis, Institute for Theoretical Computer Science, Graz University of Technology, Austria, October 2003.

[21]
Anton Schwaighofer and Volker Tresp. Transductive and inductive methods for approximate Gaussian process regression. In Advances in Neural Information Processing Systems 15, Suzanna Becker, Sebastian Thrun, and Klaus Obermayer, editors. MIT Press, 2003. .

[22]
Anton Schwaighofer, Volker Tresp, Peter Mayer, Alexander K. Scheel, and Gerhard A. Mueller. The RA scanner: Prediction of rheumatoid joint inflammation based on laser imaging. In Advances in Neural Information Processing Systems 15, Suzanna Becker, Sebastian Thrun, and Klaus Obermayer, editors. MIT Press, 2003. .

[23]
Kai Yu, Anton Schwaighofer, Volker Tresp, Wei-Ying Ma, and HongJiang Zhang. Collaborative ensemble learning: Combining collaborative and content-based information filtering via hierarchical Bayes. In Uncertainty in Artificial Intelligence: Proceedings of the 19th Conference (UAI-2003), Christopher Meek and Uffe Kjærulff, editors, pages 616-623. Morgan Kaufmann, 2003.

2002

[1]
O. Aichholzer, L.S. Alboul, and F. Hurtado. On flips in polyhedral surfaces. International Journal of Foundations of Computer Science (IJFCS), special issue on Volume and Surface Triangulations, 13(2):303-311, 2002. .

[2]
O. Aichholzer and F. Aurenhammer. Voronoi diagrams - computational geometry's favorite. Special Issue on Foundations of Information Processing of TELEMATIK, 1:7-11, 2002. .

[3]
O. Aichholzer, F. Aurenhammer, and F. Hurtado. Sequences of spanning trees and a fixed tree theorem. Computational Geometry: Theory and Applications, 21(1-2):3-20, 2002. Special Issue. [Report MA2-IR-00-00026, Universitat Politecnica de Catalunya, Barcelona, Spain, 2000]. . You can also download the nice program MST-Tool we used to check and visualize some of the presented results!

[4]
O. Aichholzer, F. Aurenhammer, and H. Krasser. On the crossing number of complete graphs. In Proc. 18th Ann. ACM Symp. Computational Geometry, pages 19-24, Barcelona, Spain, 2002. .

[5]
O. Aichholzer, F. Aurenhammer, and H. Krasser. On the crossing number of complete graphs - extended abstract. In Proc. 18th European Workshop on Computational Geometry CG '02, pages 90-92, Warszawa, Poland, 2002. .

[6]
O. Aichholzer, F. Aurenhammer, and H. Krasser. Enumerating order types for small point sets with applications. Order, 19:265-281, 2002. . See also our order type homepage.

[7]
O. Aichholzer, F. Aurenhammer, and H. Krasser. Points and combinatorics. Special Issue on Foundations of Information Processing of TELEMATIK, 1:12-17, 2002. .

[8]
O. Aichholzer, F. Aurenhammer, and H. Krasser. Progress on rectilinear crossing numbers. Technical report, IGI-TU Graz, Austria, 2002. . See also our crossing number homepage.

[9]
O. Aichholzer, F. Aurenhammer, H. Krasser, and B. Speckmann. Convexity minimizes pseudo-triangulations. In Proc. 14th Annual Canadian Conference on Computational Geometry CCCG 2002, pages 158-161, Lethbridge, Alberta, Canada, 2002. .

[10]
O. Aichholzer, F. Aurenhammer, and B. Palop. Quickest paths, straight skeletons, and the city Voronoi diagram. In Proc. 18th Ann. ACM Symp. Computational Geometry, pages 151-159, Barcelona, Spain, 2002. .

[11]
O. Aichholzer, F. Aurenhammer, and T. Werner. Algorithmic fun - Abalone. Special Issue on Foundations of Information Processing of TELEMATIK, 1:4-6, 2002. .

[12]
O. Aichholzer, D. Bremner, E.D. Demaine, F. Hurtado, E. Kranakis, H. Krasser, S. Ramaswami, S. Sethia, and J. Urrutia. Playing with triangulations. In Proc. Japan Conference on Discrete and Computational Geometry JCDCG 2002, pages 46-54, Tokyo, Japan, 2002. .

[13]
O. Aichholzer, C. Cortés, E.D. Demaine, V. Dujmovic, J. Erickson, H. Meijer, M. Overmars, B. Palop, S. Ramaswami, and G.T. Toussaint. Flipturning polygons. Discrete & Computational Geometry, 28:231-253, 2002. [Report UU-CS-2000-31, Universiteit Utrecht, The Netherlands, 2000]. . See also Jeff'shomepage about this paper.

[14]
O. Aichholzer, B. Speckmann, and I. Streinu. The path of a pseudo-triangulation. In Abstracts of the DIMACS Workshop on Computational Geometry 2002, page 2, Piscataway (NJ), USA, 2002. .

[15]
K. Andrews, W. Kienreich, V. Sabol, J. Becker, G. Droschl, F. Kappe, M. Granitzer, P. Auer, and K. Tochtermann. The InfoSky visual explorer: exploiting hierarchical structure and document similarities. Information Visualization, 1:166-181, 2002.

[16]
P. Auer. Using confidence bounds for exploitation-exploration trade-offs. J. Machine Learning Research, 3(Nov):397-422, 2002. A preliminary version has appeared in Proc. of the 41th Annual Symposium on Foundations of Computer Science.

[17]
P. Auer. Why students don't ask questions. TELEMATIK, 8(1):21-23, 2002. Special Issue on Foundations of Information Processing for the 21st Century.

[18]
P. Auer, H. Burgsteiner, and W. Maass. Reducing communication for distributed learning in neural networks. In Proc. of the International Conference on Artificial Neural Networks -- ICANN 2002, José R. Dorronsoro, editor, volume 2415 of Lecture Notes in Computer Science, pages 123-128. Springer, 2002. (Gzipped PostScript, 6 p., 117 KB). (PDF, 101 KB).

[19]
P. Auer, N. Cesa-Bianchi, Y. Freund, and R. E. Schapire. The nonstochastic multiarmed bandit problem. SIAM Journal on Computing, 32(1):48-77, 2002. A preliminary version has appeared in Proceedings of the 36th Annual Symposium on Foundations of Computer Science.

[20]
P. Auer, N. Cesa-Bianchi, and C. Gentile. Adaptive and self-confident on-line learning algorithms. JCSS, 64(1):48-75, 2002. A preliminary version has appeared in Proc. 13th Ann. Conf. Computational Learning Theory.

[21]
P. Auer, N. Cesa-Bianchi, and P. Fischer. Finite time analysis of the multiarmed bandit problem. Machine Learning, 47(2/3):235-256, 2002. A preliminary version has appeared in Proc. of the 15th International Conference on Machine Learning.

[22]
F. Aurenhammer, N. Katoh, H. Kojima, M. Ohsaki, and Y.-F. Xu. Approximating uniform triangular meshes in polygons. Theoretical Computer Science, 289:879-895, 2002. Special Issue. [SFB Report F003-159, TU Graz, Austria, 1999]. .

[23]
P. Joshi. Synthesis of a liquid state machine with hopfield/brody transient synchrony. Master's thesis, Center for Advanced Computer Studies, University of Louisiana, Lafayette, USA, November 2002.

[24]
R. A. Legenstein. The Wire-Length Complexity of Neural Networks. PhD thesis, Graz University of Technology, 2002. (Gzipped PostScript, 147 p., 1685 KB). (PDF, 2551 KB).

[25]
R. A. Legenstein. On the complexity of knock-knee channel routing with 3-terminal nets. Technical Report, 2002. (Gzipped PostScript, 24 p., 91 KB).

[26]
R. A. Legenstein and W. Maass. Neural circuits for pattern recognition with small total wire length. Theoretical Computer Science, 287:239-249, 2002. (Gzipped PostScript, 18 p., 51 KB). (PDF, 129 KB).

[27]
W. Maass. Computing with spikes. Special Issue on Foundations of Information Processing of TELEMATIK, 8(1):32-36, 2002. (PDF, 330 KB).

[28]
W. Maass. On the computational power of neural microcircuit models: Pointers to the literature. In Proc. of the International Conference on Artificial Neural Networks -- ICANN 2002, José R. Dorronsoro, editor, volume 2415 of Lecture Notes in Computer Science, pages 254-256. Springer, 2002. (PDF, 66 KB).

[29]
W. Maass. Paradigms for computing with spiking neurons. In Models of Neural Networks. Early Vision and Attention, J. L. van Hemmen, J. D. Cowan, and E. Domany, editors, volume 4, chapter 9, pages 373-402. Springer (New York), 2002. (Gzipped PostScript, 31 p., 290 KB). (PDF, 570 KB).

[30]
W. Maass, R. Legenstein, and H. Markram. A new approach towards vision suggested by biologically realistic neural microcircuit models. In Biologically Motivated Computer Vision. Proc. of the Second International Workshop, BMCV 2002, Tuebingen, Germany, November 22-24, 2002, H. H. Buelthoff, S. W. Lee, T. A. Poggio, and C. Wallraven, editors, volume 2525 of Lecture Notes in Computer Science, pages 282-293. Springer (Berlin), 2002. (PDF, 238 KB).

[31]
W. Maass and H. Markram. Synapses as dynamic memory buffers. Neural Networks, 15:155-161, 2002. (Gzipped PostScript, 12 p., 381 KB). (PDF, 216 KB).

[32]
W. Maass, T. Natschlaeger, and H. Markram. Real-time computing without stable states: A new framework for neural computation based on perturbations. Neural Computation, 14(11):2531-2560, 2002. (PDF, 1993 KB).

[33]
W. Maass, G. Steinbauer, and R. Koholka. Autonomous fast learning in a mobile robot. In Sensor Based Intelligent Robots. International Workshop, Dagstuhl Castle, Germany, October 15-25, 2000, Selected Revised Papers, G. D. Hager, H. I. Christensen, H. Bunke, and R. Klein, editors, volume 2238 of lncs, pages 345-356, 2002. (PDF, 381 KB).

[34]
T. Natschlaeger and W. Maass. Spiking neurons and the induction of finite state machines. Theoretical Computer Science: Special Issue on Natural Computing, 287:251-265, 2002. (PDF, 250 KB).

[35]
T. Natschlaeger, W. Maass, and H. Markram. The "liquid computer": A novel strategy for real-time computing on time series. Special Issue on Foundations of Information Processing of TELEMATIK, 8(1):39-43, 2002. (PDF, 277 KB).

[36]
Anton Schwaighofer. Sorting it out: Machine learning and fingerprints. Telematik, 8(1):18-20, 2002. .

[37]
A. Schwaighofer, V. Tresp, P. Mayer, A. Scheel, M. Reuss-Borst, A. Krause, I. Mesecke-von Rheinbaben, and H. Rost. Prediction of rheumatoid joint inflammation based on laser imaging using linear and kernel-based classifiers. IEEE Transactions on Biomedical Engineering, 2002. Accepted for publication. .

[38]
G. Steinbauer, R. Koholka, and W. Maass. A very short story about autonomous robots. Special Issue on Foundations of Information Processing of TELEMATIK, 8(1):26-29, 2002. (PDF, 363 KB).

[39]
Christopher K.I. Williams, Carl Edward Rasmussen, Anton Schwaighofer, and Volker Tresp. Observations on the Nystroem method for Gaussian process prediction. Technical report, Available from the authors' web pages, May 2002.

[40]
Kai Yu, Xiaowei Xu, Anton Schwaighofer, Volker Tresp, and Hans-Peter Kriegel. Removing redundancy and inconsistency in memory-based collaborative filtering. In Proceedings of the 11th International Conference on Information and Knowledge Management CIKM02, pages 52-59. ACM, 2002.

2001

[1]
O. Aichholzer, L.S. Alboul, and F. Hurtado. On flips in polyhedral surfaces. In Proc. 17th European Workshop on Computational Geometry CG '2001, pages 27-30, Berlin, Germany, 2001. . See also our interactive web-page.

[2]
O. Aichholzer, F. Aurenhammer, B. Brandtstaetter, H. Krasser, C. Magele, M. Muehlmann, and W. Renhart. Evolution trategy and ierarchical lustering. In 13th COMPUMAG Conference on the Computation of Electromagnetic Fields, Lyon-Evian, France, 2001. .

[3]
O. Aichholzer, F. Aurenhammer, F. Hurtado, and H. Krasser. Towards compatible triangulations. In Proc. 7th Ann. Int'l. Computing and Combinatorics Conf. COCOON'01, Lecture Notes in Computer Science, Jie Wang, editor, volume 2108, pages 101-110, Guilin, China, 2001. Springer Verlag. .

[4]
O. Aichholzer, F. Aurenhammer, C. Icking, R. Klein, E. Langetepe, and G. Rote. Generalized self-approaching curves. Discrete Applied Mathematics, 109(1-2):3-24, 2001. Special Issue. [SFB-Report F003-134, TU Graz, Austria, 1998]. . .

[5]
O. Aichholzer, F. Aurenhammer, and H. Krasser. On compatible triangulations of point sets. In Proc. 17th European Workshop on Computational Geometry CG '2001, pages 23-26, Berlin, Germany, 2001. .

[6]
O. Aichholzer, F. Aurenhammer, and H. Krasser. Enumerating order types for small point sets with applications. In Proc. 17th Ann. ACM Symp. Computational Geometry, pages 11-18, Medford, Massachusetts, USA, 2001. .

[7]
O. Aichholzer, D. Bremner, E.D. Demaine, D. Meijer, V. Sacristán, and M. Soss. Long proteins with unique optimal foldings in the h-p model. In Proc. 17th European Workshop on Computational Geometry CG '2001, pages 59-62, Berlin, Germany, 2001. .

[8]
O. Aichholzer, E.D. Demaine, J. Erickson, F. Hurtado, M. Overmars, M.A. Soss, and G.T. Toussaint. Reconfiguring convex polygons. Computational Geometry: Theory and Applications, 20:85-95, 2001. [Report UU-CS-2000-30, Universiteit Utrecht, The Netherlands, 2000]. . .

[9]
O. Aichholzer, F. Hurtado, and M. Noy. On the number of triangulations every planar point set must have. In Proc. 13th Annual Canadian Conference on Computational Geometry CCCG 2001, pages 13-16, Waterloo, Ontario, Canada, 2001. . See also the Counting Triangulations - Olympics.

[10]
O. Aichholzer and H. Krasser. The point set order type data base: A collection of applications and results. In Proc. 13th Annual Canadian Conference on Computational Geometry CCCG 2001, pages 17-20, Waterloo, Ontario, Canada, 2001. . See also our order type homepage.

[11]
F. Aurenhammer. Computational geometry -- some easy questions and their recent solutions. J. Universal Computer Science, 7:338-354, 2001. Special Issue. .

[12]
R. A. Legenstein and W. Maass. Foundations for a circuit complexity theory of sensory processing. In Proc. of NIPS 2000, Advances in Neural Information Processing Systems, T. K. Leen, T. G. Dietterich, and V. Tresp, editors, volume 13, pages 259-265, Cambridge, 2001. MIT Press. (Gzipped PostScript, 7 p., 40 KB). (PDF, 94 KB). The poster presented at NIPS is available as gzipped Postscript.

[13]
R. A. Legenstein and W. Maass. Optimizing the layout of a balanced tree. Technical Report, 2001. (Gzipped PostScript, 22 p., 93 KB). (PDF, 247 KB).

[14]
W. Maass. Neural computation: a research topic for theoretical computer science? Some thoughts and pointers. In Current Trends in Theoretical Computer Science, Entering the 21th Century, Rozenberg G., Salomaa A., and Paun G., editors, pages 680-690. World Scientific Publishing, 2001. (Gzipped PostScript, 11 p., 119 KB). (PDF, 223 KB).

[15]
W. Maass. wetware (English version). In TAKEOVER: Who is Doing the Art of Tomorrow (Ars Electronica 2001), pages 148-152. Springer, 2001. (PDF, 374 KB).

[16]
W. Maass. wetware (deutsche Version). In TAKEOVER: Who is Doing the Art of Tomorrow (Ars Electronica 2001), pages 153-157. Springer, 2001. (PDF, 381 KB).

[17]
W. Maass. On the relevance of time in neural computation and learning. Theoretical Computer Science, 261:157-178, 2001. (PDF, 274 KB).

[18]
T. Natschlaeger and W. Maass. Computing the optimally fitted spike train for a synapse. Neural Computation, 13(11):2477-2494, 2001. (Gzipped PostScript, 15 p., 203 KB). (PDF, 176 KB).

[19]
T. Natschlaeger and W. Maass. Finding the key to a synapse. In Advances in Neural Information Processing Systems (NIPS '2000), Todd K. Leen, Thomas G. Dietterich, and Volker Tresp, editors, volume 13, pages 138-144, Cambridge, 2001. MIT Press. (Gzipped PostScript, 7 p., 66 KB). (PDF, 124 KB). The poster presented at NIPS is available as Acrobat PDF file.

[20]
T. Natschlaeger, W. Maass, E. D. Sontag, and A. Zador. Processing of time series by neural circuits with biologically realistic synaptic dynamics. In Advances in Neural Information Processing Systems 2000 (NIPS '2000), Todd K. Leen, Thomas G. Dietterich, and Volker Tresp, editors, volume 13, pages 145-151, Cambridge, 2001. MIT Press. (Gzipped PostScript, 7 p., 60 KB). (PDF, 133 KB). The poster presented at NIPS is available as Acrobat PDF file.

[21]
T. Natschlaeger, W. Maass, and A. Zador. Efficient temporal processing with biologically realistic dynamic synapses. Network: Computation in Neural Systems, 12:75-87, 2001. (Gzipped PostScript, 14 p., 109 KB). (PDF, 213 KB).

[22]
T. Natschlaeger, B. Ruf, and M. Schmitt. Unsupervised learning and self-organization in networks of spiking neurons. In Self-Organizing Neural Networks. Recent Advances and Applications, U. Seiffert and L. C. Jain, editors, volume 78 of Springer Series on Studies in Fuzziness and Soft Computing. Springer-Verlag, Heidelberg, 2001. in press.

[23]
A. Schwaighofer and V. Tresp. The Bayesian committee support vector machine. In Artificial Neural Networks -- ICANN 2001, G. Dorffner, H. Bischof, and K. Hornik, editors, Lecture Notes in Computer Science2130, pages 411-417. Springer Verlag, 2001. .

[24]
V. Tresp and A. Schwaighofer. Scalable kernel systems. In Artificial Neural Networks -- ICANN 2001, G. Dorffner, H. Bischof, and K. Hornik, editors, Lecture Notes in Computer Science2130, pages 285-291. Springer Verlag, 2001. .

2000

[1]
O. Aichholzer. Extremal properties of 0/1-polytopes of dimension 5. In Polytopes - Combinatorics and Computation, G. Ziegler and G. Kalai, editors, pages 111-130. Birkhaeuser, 2000. [SFB-Report F003-132, TU Graz, Austria, 1998]. . You can also investigate 0/1-polytopes by e-mail!

[2]
O. Aichholzer, F. Aurenhammer, B. Brandtstaetter, T. Ebner, H. Krasser, and C. Magele. Niching evolution strategy with cluster algorithms. In 9th Biennial IEEE Conf. Electromagnetic Field Computations, Milwaukee, Wisconsin, USA, 2000. .

[3]
O. Aichholzer, F. Aurenhammer, and F. Hurtado. Edge operations on non-crossing spanning trees. In Proc. 16th European Workshop on Computational Geometry CG '2000, pages 121-125, Eilat, Israel, 2000. .

[4]
O. Aichholzer, C. Cortés, E.D. Demaine, V. Dujmovic, J. Erickson, H. Meijer, M. Overmars, B. Palop, S. Ramaswami, and G.T. Toussaint. Flipturning polygons. In Proc. Japan Conference on Discrete and Computational Geometry JCDCG 2000, Tokay University, Tokyo, Japan, 2000. . See also Jeff'shomepage about this paper.

[5]
O. Aichholzer, E.D. Demaine, J. Erickson, F. Hurtado, M. Overmars, M.A. Soss, and G.T. Toussaint. Reconfiguring convex polygons. In Proc. 12th Annual Canadian Conference on Computational Geometry CCCG 2000, pages 17-20, Fredericton, New Brunswick, Canada, 2000. .

[6]
P. Auer. An improved on-line algorithm for learning linear evaluation functions. In Proc. 13th Ann. Conf. Computational Learning Theory, pages 118-125. Morgan Kaufmann, 2000.

[7]
P. Auer. Using upper confidence bounds for online learning. In Proceedings of the 41th Annual Symposium on Foundations of Computer Science, pages 270-293. IEEE Computer Society, 2000.

[8]
P. Auer and C. Gentile. Adaptive and self-confident on-line learning algorithms. In Proc. 13th Ann. Conf. Computational Learning Theory, pages 107-117. Morgan Kaufmann, 2000.

[9]
F. Aurenhammer, N. Katoh, H. Kojima, M. Ohsaki, and Y.-F. Xu. Approximating uniform triangular meshes in polygons. In Proc. 6th Ann. Intl. Computing and Combinatorics Conference, Lecture Notes in Computer Science, volume 1558, pages 23-33, Sydney, Australia, 2000. Springer Verlag. .

[10]
F. Aurenhammer and R. Klein. Voronoi diagrams. In Handbook of Computational Geometry, Chapter V, J. Sack and G. Urrutia, editors, pages 201-290. Elsevier Science Publishing, 2000. [SFB Report F003-092, TU Graz, Austria, 1996]. .

[11]
F. Aurenhammer and Y.-F.Xu. Optimal triangulations. In Encyclopedia of Optimization, P.M.Pardalos C.A.Floudas, editor, volume 4, pages 160-166. Kluwer Academic Publishing, 2000. [SFB Report F003-099, Tu Graz, Austria, 1998]. .

[12]
W. Maass. Spike trains -- im Rhythmus neuronaler Zellen. In Katalog der steirischen Landesausstellung gr2000az, R. Kriesche H. Konrad, editor, pages 36-42. Springer Verlag, 2000.

[13]
W. Maass. Lernende Maschinen. In Katalog der steirischen Landesausstellung gr2000az, R. Kriesche H. Konrad, editor, pages 50-56. Springer Verlag, 2000.

[14]
W. Maass. Neural computation: a research topic for theoretical computer science? Some thoughts and pointers. In Bulletin of the European Association for Theoretical Computer Science (EATCS), volume 72, pages 149-158, 2000.

[15]
W. Maass. Neural computation with winner-take-all as the only nonlinear operation. In Advances in Information Processing Systems, Sara A. Solla, Todd K. Leen, and Klaus-Robert Mueller, editors, volume 12, pages 293-299. MIT Press (Cambridge), 2000. (Gzipped PostScript, 7 p., 85 KB). (PDF, 75 KB).

[16]
W. Maass. Das menschliche Gehirn -- nur ein Rechner?. In Zur Kunst des Formalen Denkens, R. E. Burkard, W. Maass, and P. Weibel, editors, pages 209-233. Passagen Verlag (Wien), 2000. (Gzipped PostScript, 20 p., 153 KB). (PDF, 206 KB).

[17]
W. Maass. On the computational power of winner-take-all. Neural Computation, 12(11):2519-2535, 2000. (Gzipped PostScript, 19 p., 160 KB). (PDF, 98 KB).

[18]
W. Maass and T. Natschlaeger. A model for fast analog computation based on unreliable synapses. Neural Computation, 12(7):1679-1704, 2000. (Gzipped PostScript, 26 p., 211 KB). (PDF, 1304 KB).

[19]
W. Maass, A. Pinz, R. Braunstingl, G. Wiesspeiner, T. Natschlaeger, O. Friedl, and H. Burgsteiner. Konstruktion von lernfaehigen mobilen Robotern im Studentenwettbewerb ``Robotik 2000'' an der Technischen Universitaet Graz. in: Telematik, pages 20-24, 2000. (Gzipped PostScript, 8 p., 83 KB). (PDF, 557 KB).

[20]
W. Maass and E. D. Sontag. Neural systems as nonlinear filters. Neural Computation, 12(8):1743-1772, 2000. (Gzipped PostScript, 26 p., 107 KB). (PDF, 172 KB).

[21]
A. Schwaighofer. Fingerprint matching with spectral features. Master's thesis, Institute for Theoretical Computer Science, Graz University of Technology, Austria, May 2000.

1999

[1]
O. Aichholzer. The path of a triangulation. In Proc. 15th Ann. ACM Symp. Computational Geometry, pages 14-23, Miami Beach, Florida, USA, 1999. . For an implementation see my page on triangulation counting.

[2]
O. Aichholzer, F. Aurenhammer, D.Z. Chen, D.T. Lee, and E. Papadopoulou. Skew Voronoi diagrams. Int'l. Journal of Computational Geometry & Applications, 9:235-247, 1999. . Click here for Figures and Animations of Skew Voronoi Diagrams

[3]
O. Aichholzer, F. Aurenhammer, and R. Hainz. New results on MWT subgraphs. Information Processing Letters, 69:215-219, 1999. [SFB Report F003-140, TU Graz, Austria, 1998]. .

[4]
O. Aichholzer, F. Aurenhammer, G. Rote, and Y.-F. Xu. Constant-level greedy triangulations approximate the MWT well. Journal of Combinatorial Optimization, 2:361-369, 1999. [SFB-Report F003-050, TU Graz, Austria, 1995]. .

[5]
P. Auer, N. Cesa-Bianchi, and P. Fischer. Finite time analysis of the multiarmed bandit problem. In IT Workshop on Decision, Estimation, Classification and Imaging, Santa Fe, Feb 1999.

[6]
P. Auer and P. M. Long. Structural results about on-line learning models with and without queries. Machine Learning, 36:147-181, 1999. A preliminary version has appeared in Proceedings of the 26th ACM Symposium on the Theory of Computing.

[7]
H. Burgsteiner. Integration of xvision and khepera. Technical report, Institute for Theoretical Computer Science, Graz University of Technology, 1999. . .

[8]
H. Krasser. Kompatible triangulierungen ebener punktmengen. Master's thesis, Institute for Theoretical Computer Science, Graz University of Technology, Austria, June 1999. (in German). .

[9]
R. A. Legenstein. Effizientes Layout von Neuronalen Netzen. Master's thesis, Technische Universitaet Graz, September 1999. (Gzipped PostScript, 77 p., 207 KB).

[10]
W. Maass. Computing with spiking neurons. In Pulsed Neural Networks, W. Maass and C. M. Bishop, editors, pages 55-85. MIT Press (Cambridge), 1999. (Gzipped PostScript, 31 p., 666 KB). (PDF, 771 KB).

[11]
W. Maass and B. Ruf. On computation with pulses. Information and Computation, 148:202-218, 1999. (Gzipped PostScript, 20 p., 164 KB). (PDF, 196 KB).

[12]
W. Maass and M. Schmitt. On the complexity of learning for spiking neurons with temporal coding. Information and Computation, 153:26-46, 1999. (Gzipped PostScript, 24 p., 136 KB). (PDF, 267 KB).

[13]
W. Maass and E. Sontag. Analog neural nets with Gaussian or other common noise distributions cannot recognize arbitrary regular languages. Neural Computation, 11:771-782, 1999. (Gzipped PostScript, 12 p., 104 KB). (PDF, 109 KB).

[14]
W. Maass and E. D. Sontag. A precise characterization of the class of languages recognized by neural nets under Gaussian and other common noise distributions. In Advances in Neural Information Processing Systems, M. S. Kearns, S. S. Solla, and D. A. Cohn, editors, volume 11, pages 281-287. MIT Press (Cambridge), 1999. (Gzipped PostScript, 7 p., 45 KB). (PDF, 108 KB).

[15]
W. Maass and A. M. Zador. Dynamic stochastic synapses as computational units. Neural Computation, 11(4):903-917, 1999. (Gzipped PostScript, 18 p., 223 KB). (PDF, 228 KB).

[16]
T. Natschlaeger. Efficient Computation in Networks of Spiking Neurons -- Simulations and Theory. PhD thesis, Graz University of Technology, 1999. (Gzipped PostScript, 116 p., 1289 KB).

[17]
T. Natschlaeger and W. Maass. Fast analog computation in networks of spiking neurons using unreliable synapses. In ESANN'99 Proceedings of the European Symposium on Artificial Neural Networks, pages 417-422, Bruges, Belgium, 1999. (Gzipped PostScript, 6 p., 79 KB). (PDF, 180 KB).

[18]
T. Natschlaeger and B. Ruf. Pattern analysis with spiking neurons using delay coding. Neurocomputing, 26-27(1-3):463-469, 1999. (Gzipped PostScript, 7 p., 87 KB).

1998

[1]
O. Aichholzer. Efficient {0,1}-string searching based on pre-clustering. In Proc. 14th European Workshop on Computational Geometry CG '98, pages 11-13, Barcelona, Spain, 1998. [SFB Report F003-94, TU Graz, Austria, 1996]. .

[2]
O. Aichholzer and F. Aurenhammer. Straight skeletons for general polygonal figures in the plane. In Voronoi's Impact on Modern Sciences II, A.M. Samoilenko, editor, volume 21, pages 7-21. Proc. Institute of Mathematics of the National Academy of Sciences of Ukraine, Kiev, Ukraine, 1998. .

[3]
O. Aichholzer, F. Aurenhammer, C. Icking, R. Klein, E. Langetepe, and G. Rote. Generalized self-approaching curves. In Proc. 14th European Workshop on Computational Geometry CG '98, pages 15-18, Barcelona, Spain, 1998. .

[4]
O. Aichholzer, F. Aurenhammer, C. Icking, R. Klein, E. Langetepe, and G. Rote. Generalized self-approaching curves. In Proc. 9th Int. Symp. Algorithms and Computation ISAAC'98, Lecture Notes in Computer Science, volume 1533, pages 317-326, Taejon, Korea, 1998. Springer Verlag. .

[5]
P. Auer. On learning from ambiguous information. Periodica Polytechnica Electrical Engineering, 42(1):115-122, 1998.

[6]
P. Auer. Some thoughts on boosting and neural networks. In Beitraege zum 3. Cottbuser Workshop `Aspekte des Neuronalen Lernens' CoWAN'98, L. Cromme, T. Kolb, and H. Koch, editors, pages 11-28, Cottbus, Germany, October 1998. Shaker Verlag. Invited paper.

[7]
P. Auer and N. Cesa-Bianchi. On-line learning with malicious noise and the closure algorithm. Annals of Mathematics and Artificial Intelligence, 23:83-99, 1998. A preliminary version has appeared in Lecture Notes in Artificial Intelligence 872, Springer.

[8]
P. Auer, P. M. Long, and A. Srinivasan. Approximating hyper-rectangles: Learning and pseudorandom sets. Journal of Computer and System Sciences, 57(3):376-388, 1998. A preliminary version has appeared in Proc. 29th Ann. Symp. Theory of Computing.

[9]
P. Auer and W. Maass. Introduction to the special issue on computational learning theory. Algorithmica, 22(1/2):1-2, 1998. (PDF, 18 KB).

[10]
P. Auer and M. K. Warmuth. Tracking the best disjunction. Machine Learning, 32:127-150, 1998. A preliminary version has appeared in Proceedings of the 36th Annual Symposium on Foundations of Computer Science.

[11]
F. Aurenhammer, F. Hoffmann, and B. Aronov. Minkowski-type theorems and least-squares clustering. Algorithmica, 20:61-76, 1998. [SFB Report F003-075, TU Graz, Austria, 1996]. .

[12]
H. Burgsteiner. Neural Networks with Spiking Neurons. Master's thesis, Graz University of Technology, November 1998. . .

[13]
W. Maass. On the role of time and space in neural computation. In Proc. of the Federated Conference of CLS'98 and MFCS'98, Mathematical Foundations of Computer Science 1998, volume 1450 of Lecture Notes in Computer Science, pages 72-83. Springer (Berlin), 1998. Invited talk. (Gzipped PostScript, 14 p., 188 KB). (PDF, 729 KB).

[14]
W. Maass. A simple model for neural computation with firing rates and firing correlations. Network: Computation in Neural Systems, 9(3):381-397, 1998. (PDF, 288 KB).

[15]
W. Maass. Models for fast analog computation with spiking neurons. In Proc. of the International Conference on Neural Information Processing 1998 (ICONIP'98) in Kytakyusyu, Japan, pages 187-188. IOS Press (Amsterdam), 1998. Invited talk at the special session on ``Dynamic Brain''.

[16]
W. Maass. Spiking neurons. In Proceedings of the ICSC/IFAC Symposium on Neural Computation 1998 (NC'98), pages 16-20. ICSC Academic Press (Alberta), 1998. Invited talk.

[17]
W. Maass and T. Natschlaeger. Associative memory with networks of spiking neurons in temporal coding. In Neuromorphic Systems: Engineering Silicon from Neurobiology, L. S. Smith and A. Hamilton, editors, pages 21-32. World Scientific, 1998. (Gzipped PostScript, 13 p., 103 KB). (PDF, 253 KB).

[18]
W. Maass and T. Natschlaeger. Emulation of Hopfield networks with spiking neurons in temporal coding. In Computational Neuroscience: Trends in Research, J. M. Bower, editor, pages 221-226. Plenum Press, 1998. (Gzipped PostScript, 7 p., 82 KB). (PDF, 187 KB).

[19]
W. Maass and P. Orponen. On the effect of analog noise in discrete-time analog computations. Neural Computation, 10:1071-1095, 1998. (Gzipped PostScript, 19 p., 109 KB). (PDF, 163 KB).

[20]
W. Maass and M. Warmuth. Efficient learning with virtual threshold gates. Information and Computation, 141(1):66-83, 1998. (Gzipped PostScript, 14 p., 54 KB). (PDF, 439 KB).

[21]
W. Maass and A. Zador. Computing and learning with dynamic synapses. In Pulsed Neural Networks, W. Maass and C. Bishop, editors, pages 321-336. MIT-Press (Cambridge), 1998. (Gzipped PostScript, 16 p., 516 KB). (PDF, 869 KB).

[22]
W. Maass and A. M. Zador. Dynamic stochastic synapses as computational units. In Advances in Neural Processing Systems, volume 10, pages 194-200. MIT Press (Cambridge), 1998. (Gzipped PostScript, 571 KB). (PDF, 624 KB).

[23]
T. Natschlaeger. Networks of spiking neurons: A new generation of neural network models. In Jenseits von Kunst. Passagen Verlag, 1998. (Gzipped PostScript, 211 KB). Online version

[24]
T. Natschlaeger and B. Ruf. Spatial and temporal pattern analysis via spiking neurons. Network: Computation in Neural Systems, 9(3):319-332, 1998. (Gzipped PostScript, 15 p., 179 KB).

[25]
T. Natschlaeger and B. Ruf. Online clustering with spiking neurons using temporal coding. In Neuromorphic Systems: Engineering Silicon from Neurobiology, L. S. Smith and A. Hamilton, editors, pages 33-42. World Scientific, 1998. (Gzipped PostScript, 10 p., 92 KB).

[26]
B. Ruf. Computing and learning with spiking neurons - theory and simulations. PhD thesis, TU Graz, 1998.

[27]
B. Ruf. Networks of spiking neurons can compute linear functions using action potential timing. In Proc. of the VI-Dynn 98 conference, T. Lindblad, editor. Spie, 1998.

[28]
B. Ruf and M. Schmitt. Self-organization of spiking neurons using action potential timing. IEEE Transactions on Neural Networks, 9:3:575-578, 1998. .

[29]
B. Ruf and M. Schmitt. Self-organizing maps of spiking neurons using temporal coding. In Computational Neuroscience: Trends in Research 1998 (to appear), J. Bower, editor. Plenum Press, 1998. .

1997

[1]
O. Aichholzer. Combinatorial & Computational Properties of the Hypercube - New Results on Covering, Slicing, Clustering and Searching on the Hypercube. PhD thesis, IGI-TU Graz, Austria, 1997. .

[2]
O. Aichholzer. The path of a triangulation. In Proc. 13th European Workshop on Computational Geometry CG '97, pages 1-3, Wuerzburg, Germany, 1997. . For an implementation see my page on triangulation counting.

[3]
O. Aichholzer, H. Alt, and G. Rote. Matching shapes with a reference point. Int'l Journal of Computational Geometry & Applications, 7(4):349-363, 1997. .

[4]
O. Aichholzer, F. Aurenhammer, D.Z. Chen, D.T. Lee, A. Mukhopadhyay, and E. Papadopoulou. Voronoi diagrams for direction-sensitive distances (communication). In Proc. 13th Ann. ACM Symp. Computational Geometry, pages 418-420, Nice, France, 1997. [SFB Report F003-098, TU Graz, Austria, 1996]. .

[5]
P. Auer. Learning nested differences in the presence of malicious noise. Theoretical Computer Science, 185:159-175, 1997. A preliminary version has appeared in Proceedings of the 6th International Workshop on Algorithmic Learning Theory, ALT`95.

[6]
P. Auer. On learning from multi-instance examples: Empirical evaluation of a theoretical approach. In Proc. 14th Int. Conf. Machine Learning, D. H. Fisher, editor, pages 21-29. Morgan Kaufmann, 1997.

[7]
P. Auer, P. M. Long, and A. Srinivasan. Approximating hyper-rectangles: Learning and pseudo-random sets. In Proc. 29th Ann. Symp. Theory of Computing, pages 314-323. ACM, May 1997.

[8]
R. Hainz, O. Aichholzer, and F. Aurenhammer. New results on minimum-weight triangulations and the LMT skeleton. In Proc. 13th European Workshop on Computational Geometry CG '97, pages 4-6, Wuerzburg, Germany, 1997. .

[9]
J. Kivinen, M. K. Warmuth, and P. Auer. The perceptron algorithm vs. Winnow: linear vs. logarithmic mistake bounds when few input variables are relevant. Artificial Intelligence, pages 325-343, 1997.

[10]
E. Kranakis, D. Krizanc, B. Ruf, J. Urrutia, and G. Woeginger. The VC-dimension of set-systems defined by graphs. Journal of Discrete Applied Mathematics, 77:237-257, 1997. .

[11]
W. Maass. Bounds for the computational power and learning complexity of analog neural nets. SIAM J. on Computing, 26(3):708-732, 1997. (Gzipped PostScript, 32 p., 173 KB). (PDF, 412 KB).

[12]
W. Maass. Fast sigmoidal networks via spiking neurons. Neural Computation, 9:279-304, 1997. (Gzipped PostScript, 27 p., 207 KB). (PDF, 2139 KB).

[13]
W. Maass. Networks of spiking neurons: the third generation of neural network models. Neural Networks, 10:1659-1671, 1997. (Gzipped PostScript, 27 p., 205 KB). (PDF, 1308 KB).

[14]
W. Maass. A model for fast analog computations with noisy spiking neurons. In Computational Neuroscience: Trends in research, James Bower, editor, pages 123-127, 1997. (Gzipped PostScript, 6 p., 45 KB). (PDF, 113 KB).

[15]
W. Maass. Analog computations with temporal coding in networks of spiking neurons. In Spatiotemporal Models in Biological and Artificial Systems, F. L. Silva, editor, pages 97-104. IOS-Press, 1997.

[16]
W. Maass. Noisy spiking neurons with temporal coding have more computational power than sigmoidal neurons. In Advances in Neural Information Processing Systems, M. Mozer, M. I. Jordan, and T. Petsche, editors, volume 9, pages 211-217. MIT Press (Cambridge), 1997. (Gzipped PostScript, 13 p., 161 KB). (PDF, 389 KB).

[17]
W. Maass. On the relevance of time in neural computation and learning. In Proc. of the 8th International Conference on Algorithmic Learning Theory in Sendai (Japan), M. Li and A. Maruoka, editors, volume 1316 of Lecture Notes in Computer Science, pages 364-384. Springer (Berlin), 1997. (Gzipped PostScript, 24 p., 212 KB). (PDF, 410 KB).

[18]
W. Maass and T. Natschlaeger. Networks of spiking neurons can emulate arbitrary Hopfield nets in temporal coding. Network: Computation in Neural Systems, 8(4):355-371, 1997. (Gzipped PostScript, 19 p., 188 KB). (PDF, 433 KB).

[19]
W. Maass and P. Orponen. On the effect of analog noise in discrete-time analog computations. In Advances in Neural Information Processing Systems, M. Mozer, M. I. Jordan, and T. Petsche, editors, volume 9, pages 218-224. MIT Press (Cambridge), 1997. (Gzipped PostScript, 7 p., 71 KB). (PDF, 180 KB).

[20]
W. Maass and M. Schmitt. On the complexity of learning for a spiking neuron. In Proc. of the 10th Conference on Computational Learning Theory 1997, pages 54-61. ACM-Press (New York), 1997. See also Electronic Proc. of the Fifth International Symposium on Artificial Intelligence and Mathematics (http://rutcor.rutgers.edu/~amai). (PDF, 1323 KB).

[21]
W. Maass and P. Weibel. Ist die Vertreibung der Vernunft reversibel? Ueberlegungen zu einem Wissenschafts- und Medienzentrum. In Jenseits von Kunst, P. Weibel, editor, pages 745-747. Passagen Verlag, 1997. (Gzipped PostScript, 9 p., 18 KB). (PDF, 52 KB).

[22]
B. Ruf. Computing functions with spiking neurons in temporal coding. In Biological and artificial computation: From neuroscience to technology, J. Mira, R. Moreno-Diaz, and J. Cabestany, editors, volume 1240 of Lecture Notes in Computer Science, pages 265-272. Springer, Berlin, 1997. .

[23]
B. Ruf and M. Schmitt. Learning temporally encoded patterns in networks of spiking neurons. Neural Processing Letters, 5(1):9-18, 1997.

[24]
B. Ruf and M. Schmitt. Hebbian learning in networks of spiking neurons using temporal coding. In Biological and artificial computation: From neuroscience to technology, J. Mira, R. Moreno-Diaz, and J. Cabestany, editors, volume 1240 of Lecture Notes in Computer Science, pages 380-389. Springer, Berlin, 1997. .

[25]
B. Ruf and M. Schmitt. Unsupervised learning in networks of spiking neurons using temporal coding. In Proc. of the 7th International Conference on Artificial Neural Networks, W. Gerstner, A. Germond, M. Hasler, and J. Nicoud, editors, volume 1327 of Lecture Notes in Computer Science, pages 361-366. Springer, Berlin, 1997. .

1996

[1]
O. Aichholzer. Clustering the hypercube. SFB-Report F003-93, SFB 'Optimierung und Kontrolle', TU Graz, Austria, 1996. .

[2]
O. Aichholzer and F. Aurenhammer. Classifying hyperplanes in hypercubes. SIAM Journal on Discrete Mathematics, 9(2):225-232, 1996. [IIG-Report-Series 408, TU Graz, Austria, 1995]. .

[3]
O. Aichholzer and F. Aurenhammer. Straight skeletons for general polygonal figures. In Proc. 2nd Ann. Int'l. Computing and Combinatorics Conf. COCOON'96, Lecture Notes in Computer Science, volume 1090, pages 117-126, Hong Kong, 1996. Springer Verlag. [IIG-Report-Series 423, TU Graz, Austria, 1995]. .

[4]
O. Aichholzer, F. Aurenhammer, S.-W. Cheng, N. Katoh, G. Rote, M. Taschwer, and Y.-F. Xu. Triangulations intersect nicely. Discrete & Computational Geometry, 16:339-359, 1996. Special Issue. [SFB Report F003-030, TU Graz, Austria, 1995]. .

[5]
O. Aichholzer, F. Aurenhammer, G. Rote, and Y.-F. Xu. Constant-level greedy triangulations approximate the MWT well. In Proc. 2nd Int'l. Symp. Operations Research & Applications ISORA'96, Lecture Notes in Operations Research, Cheng Du, Zhang, editor, volume 2, pages 309-318, Guilin, P. R. China, 1996. World Publishing Corporation. .

[6]
O. Aichholzer, F. Aurenhammer, G. Rote, and Y.-F. Xu. New greedy triangulation algorithms. In Proc. 12th European Workshop on Computational Geometry CG '96, pages 11-14, Muenster, Germany, 1996. .

[7]
P. Auer, P. Caianiello, and N. Cesa-Bianchi. Tight bounds on the cumulative profit of distributed voters. In Proceedings of the 15th Annual ACM Symposium on Principles of Distributed Computing, page 312, 1996. Abstract.

[8]
P. Auer, M. Herbster, and M. K. Warmuth. Exponentially many local minima for single neurons. In Advances in Neural Information Processing Systems 8, D. S. Touretzky, M. C. Mozer, and M. E. Hasselmo, editors, pages 316-322. MIT Press, 1996.

[9]
P. Auer and K. Hornik. The number of points of an empirical or Poisson process covered by unions of sets. Journal of Multivariate Analysis, 57:37-51, 1996.

[10]
P. Auer and K. Hornik. Limit laws for the maximal and minimal increments of the Poisson process. Studia Scientiarum Mathematicarum Hungarica, 31:1-13, 1996.

[11]
P. Auer, S. Kwek, W. Maass, and M. K. Warmuth. Learning of depth two neural nets with constant fan-in at the hidden nodes. In Proc. of the 9th Conference on Computational Learning Theory 1996, pages 333-343. ACM-Press (New York), 1996. (Gzipped PostScript, 12 p., 101 KB). (PDF, 256 KB).

[12]
D. P. Dobkin, D. Gunopulos, and W. Maass. Computing the maximum bichromatic discrepancy, with applications to computer graphics and machine learning. Journal of Computer and System Sciences, 52(3):453-470, June 1996. (Gzipped PostScript, 38 p., 152 KB). (PDF, 813 KB).

[13]
W. Maass. Analog computations on networks of spiking neurons (extended abstract). In Proc. of the 7th Italian Workshop on Neural Nets 1995, pages 99-104. World Scientific (Singapore), 1996. (PDF, 170 KB).

[14]
W. Maass. Lower bounds for the computational power of networks of spiking neurons. Neural Computation, 8(1):1-40, 1996. (Gzipped PostScript, 39 p., 337 KB). (PDF, 2234 KB).

[15]
W. Maass. On the computational power of noisy spiking neurons. In Advances in Neural Information Processing Systems, D. Touretzky, M. C. Mozer, and M. E. Hasselmo, editors, volume 8, pages 211-217. MIT Press (Cambridge), 1996. (Gzipped PostScript, 9 p., 90 KB). (PDF, 579 KB).

[16]
W. Maass. Networks of spiking neurons: the third generation of neural network models. In Proc. of the 7th Australian Conference on Neural Networks 1996 in Canberra, Australia, pages 1-10, 1996. (PDF, 778 KB).

[17]
T. Natschlaeger. Raum- zeitliche Strukturen von Berechnungen in biologisch realistischen neuronalen Netzwerken. Master's thesis, Technische Universitaet Graz, February 1996. (Gzipped PostScript, 129 p., 675 KB).

[18]
T. Natschlaeger. Netzwerke von Spiking Neuronen: Die dritte Generation von Modellen fuer neuronale Netzwerke. In Jenseits von Kunst. Passagen Verlag, 1996. (Gzipped PostScript, 10 p., 194 KB). Online version

[19]
T. Natschlaeger and M. Schmitt. Exact VC-Dimension of boolean monomials. Information Processing Letters, 59:19-20, 1996. (Gzipped PostScript, 4 p., 41 KB).

[20]
B. Ruf. Pattern recognition with networks of spiking neurons. In Workshop on Neural Networks Dynamics and Pattern Recognition, Toulouse, pages 25-26. Onera, Centre d'Etudes et de Recherches de Toulouse, 1996. .

1995

[1]
O. Aichholzer. Local properties of triangulations. In Proc. 11th European Workshop on Computational Geometry CG '95, pages 27-30, Hagenberg/Linz, Austria, 1995. .

[2]
O. Aichholzer, D. Alberts, F. Aurenhammer, and B. Gaertner. A novel type of skeleton for polygons. Journal of Universal Computer Science, 1(12):752-761, 1995. [IIG-Report-Series 424, TU Graz, Austria, 1995]. . Click here for the Online Version

[3]
O. Aichholzer, D. Alberts, F. Aurenhammer, and B. Gaertner. Straight skeletons of simple polygons. In Proc. 4th Int. Symp. of LIESMARS, pages 114-124, Wuhan, P. R. China, 1995. .

[4]
O. Aichholzer, F. Aurenhammer, and G. Rote. Optimal graph orientation with storage applications. SFB-Report F003-51, SFB 'Optimierung und Kontrolle', TU Graz, Austria, 1995. .

[5]
O. Aichholzer, F. Aurenhammer, G. Rote, and M. Taschwer. Triangulations intersect nicely. In Proc. 11th Ann. ACM Symp. Computational Geometry, pages 220-229, Vancouver, Canada, 1995. .

[6]
O. Aichholzer, R.L.S. Drysdale, and G. Rote. A simple linear time greedy triangulation algorithm for uniformly distributed points. IIG-Report-Series 408, TU Graz, Austria, 1995. Presented at the Workshop on Computational Geometry, Army MSI Cornell, Stony Brook, 1994. .

[7]
P. Auer. Learning nested differences in the presence of malicious noise. In 6th International Workshop, ALT`95, Proceedings, Klaus P. Jantke, Takeshi Shinohara, and Thomas Zeugmann, editors, pages 123-137. Springer, 1995. LNAI 997.

[8]
P. Auer, N. Cesa-Bianchi, Y. Freund, and R. E. Schapire. Gambling in a rigged casino: The adversarial multi-armed bandit problem. In Proceedings of the 36th Annual Symposium on Foundations of Computer Science, pages 322-331. IEEE Computer Society Press, Los Alamitos, CA, 1995.

[9]
P. Auer, R. C. Holte, and W. Maass. Theory and applications of agnostic PAC-learning with small decision trees. In Proc. of the 12th International Machine Learning Conference, Tahoe City (USA), pages 21-29. Morgan Kaufmann (San Francisco), 1995. (Gzipped PostScript, 14 p., 64 KB). (PDF, 219 KB).

[10]
P. Auer, P. M. Long, W. Maass, and G. J. Woeginger. On the complexity of function learning. Machine Learning, 18:187-230, 1995. Invited paper in a special issue of Machine Learning. (PDF, 2394 KB).

[11]
P. Auer and M. K. Warmuth. Tracking the best disjunction. In Proceedings of the 36th Annual Symposium on Foundations of Computer Science, pages 312-321. IEEE Computer Society Press, 1995.

[12]
F. Aurenhammer. Guest editor's foreword of the special issue on computational geometry. Int'l Journal of Computational Geometry & Applications, 5:1, 1995.

[13]
F. Aurenhammer and J. Hagauer. Recognizing binary Hamming graphs in O(n2 log n) time. Mathematical Systems Theory, 28:387-395, 1995. [IIG-Report-Series 273, TU Graz, Austria, 1989]. .

[14]
W. J. Bultman and W. Maass. Fast identification of geometric objects with membership queries. Information and Computation, 118:48-64, 1995. (PDF, 1276 KB).

[15]
E. Kranakis, D. Krizanc, B. Ruf, J. Urrutia, and G. Woeginger. VC-dimensions for graphs. In Graph-theoretic concepts in computer science, M. Nagl, editor, volume 1017 of Lecture Notes in Computer Science, pages 1-13. Springer (Berlin), 1995. .

[16]
W. Maass. Agnostic PAC-learning of functions on analog neural nets. In Advances in Neural Information Processing Systems, volume 7, pages 311-318, 1995. (Gzipped PostScript, 266 KB). (PDF, 269 KB).

[17]
W. Maass. Agnostic PAC-learning of functions on analog neural nets. Neural Computation, 7:1054-1078, 1995. (Gzipped PostScript, 22 p., 82 KB). (PDF, 1517 KB).

[18]
W. Maass. Vapnik-Chervonenkis dimension of neural nets. In The Handbook of Brain Theory and Neural Networks, M. A. Arbib, editor, pages 1000-1003. MIT Press (Cambridge), 1995. (Gzipped PostScript, 10 p., 43 KB). (PDF, 163 KB).

[19]
W. Maass. On the computational complexity of networks of spiking neurons. In Advances in Neural Information Processing Systems, G. Tesauro, D. S. Touretzky, and T. K. Leen, editors, volume 7, pages 183-190. MIT Press (Cambridge), 1995. (Gzipped PostScript, 19 p., 63 KB). (PDF, 209 KB).

[20]
W. Maass. Neuronale Netze und maschinelles Lernen am Institut fuer Grundlagen der Informationsverarbeitung an der Technischen Universitaet Graz. Telematik, 2:53-60, 1995. (PDF, 2024 KB).

[21]
W. Maass and B. Ruf. On the relevance of the shape of postsynaptic potentials for the computational power of networks of spiking neurons. In Proc. of the International Conference on Artificial Neural Networks ICANN, pages 515-520, Paris, 1995. EC2&Cie. (Gzipped PostScript, 6 p., 35 KB). (PDF, 152 KB).

[22]
W. Maass and G. Turan. On learnability and predicate logic (extended abstract). In Proc. of the 4th Bar-Ilan Symposium on Foundations of Artificial Intelligence (BISFAI'95), pages 126-136, Jerusalem, 1995. (PDF, 541 KB).

[23]
W. Maass and M. Warmuth. Efficient learning with virtual threshold gates. In Proc. of the 12th International Machine Learning Conference, Tahoe City, USA, Morgan Kaufmann (San Francisco), editor, pages 378-386, 1995.

1994

[1]
O. Aichholzer, H. Alt, and G. Rote. Matching shapes with a reference point. In Proc. 10th Ann. ACM Symp. Computational Geometry, pages 85-92, Stony Brook, New York, USA, 1994. .

[2]
O. Aichholzer, H. Alt, and G. Rote. Matching shapes with a reference point. In Proc. 10th European Workshop on Computational Geometry CG '94, pages 81-84, Santander, Spain, 1994. .

[3]
O. Aichholzer and F. Aurenhammer. Classifying hyperplanes in hypercubes. In Proc. 10th European Workshop on Computational Geometry CG '94, pages 53-57, Santander, Spain, 1994. .

[4]
P. Auer and N. Cesa-Bianchi. On-line learning with malicious noise and the closure algorithm. In Algorithmic Learning Theory, AII'94, ALT'94, Setsuo Arikawa and Klaus P. Jantke, editors, pages 229-247. Lecture Notes in Artificial Intelligence 872, Springer, 1994.

[5]
P. Auer and K. Hornik. On the number of points of a homogeneous Poisson process. Journal of Multivariate Analysis, 48(1):115-156, 1994.

[6]
P. Auer and P. M. Long. Simulating access to hidden information while learning. In Proceedings of the 26th Annual ACM Symposium on the Theory of Computing, pages 263-272. ACM Press, 1994.

[7]
F. Aurenhammer, M. Formann, R. Idury, A. Schaeffer, and F. Wagner. Faster isometric embedding in products of complete graphs. Discrete Applied Mathematics, 52:17-28, 1994. [Report B-90-06, FU Berlin, Germany, 1990]. .

[8]
Z. Chen and W. Maass. On-line learning of rectangles and unions of rectangles. Machine Learning, 17:201-223, 1994. Invited paper for a special issue of Machine Learning. (Gzipped PostScript, 15 p., 220 KB). (PDF, 1301 KB).

[9]
K. Hornik, M. Stinchcombe, H. White, and P. Auer. Degree of approximation results for feedforward networks approximating unknown mappings and their derivatives. Neural Computation, 6:1262-1275, 1994.

[10]
W. Maass. Neural nets with superlinear VC-dimension. In Proceedings of the International Conference on Artificial Neural Networks 1994 (ICANN'94), pages 581-584. Springer (Berlin), 1994. (PDF, 631 KB).

[11]
W. Maass. Perspectives of current research about the complexity of learning on neural nets. In Theoretical Advances in Neural Computation and Learning, V. P. Roychowdhury, K. Y. Siu, and A. Orlitsky, editors, pages 295-336. Kluwer Academic Publishers (Boston), 1994. (Gzipped PostScript, 37 p., 115 KB). (PDF, 356 KB).

[12]
W. Maass. Computing on analog neural nets with arbitrary real weights. In Theoretical Andvances in Neural Computation and Learning, V. P. Roychowdhury, K. Y. Siu, and A. Orlitsky, editors, pages 153-172. Kluwer Academics Publisher (Boston), 1994. (Gzipped PostScript, 17 p., 102 KB). (PDF, 256 KB).

[13]
W. Maass. Efficient agnostic PAC-learning with simple hypotheses. In Proc. of the 7th Annual ACM Conference on Computational Learning Theory, pages 67-75, 1994. (Gzipped PostScript, 9 p., 53 KB). (PDF, 170 KB).

[14]
W. Maass. On the complexity of learning on neural nets. In Computational Learning Theory: EuroColt'93, J. Shawe-Taylor and M. Anthony, editors, pages 1-17. Oxford University Press (Oxford), 1994. (Gzipped PostScript, 17 p., 63 KB). (PDF, 237 KB).

[15]
W. Maass. Neural nets with superlinear VC-dimension. Neural Computation, 6:877-884, 1994. (Gzipped PostScript, 9 p., 43 KB). (PDF, 448 KB).

[16]
W. Maass, G. Schnitger, and E. Sontag. A comparison of the computational power of sigmoid and boolean threshold circuits. In Theoretical Advances in Neural Computation and Learning, V. P. Roychowdhury, K. Y. Siu, and A. Orlitsky, editors, pages 127-151. Kluwer Academic Publishers (Boston), 1994. (PDF, 305 KB).

[17]
W. Maass and G. Turan. How fast can a threshold gate learn. In Computational Learning Theory and Natural Learning System: Constraints and Prospects, S. J. Hanson, G. A. Drastal, and R. L. Rivest, editors, pages 381-414. MIT Press (Cambridge), 1994. (PDF, 2200 KB).

[18]
W. Maass and G. Turan. Algorithms and lower bounds for on-line learning of geometrical concepts. Machine Learning, 14:251-269, 1994. (PDF, 1588 KB).

[19]
B. Ruf. A stop criterion for the boltzmann machine learning algorithm. In Proc. of the 2nd european symposium on artificial neural networks, M. Verleysen, editor, pages 109-116, Brussels, 1994. .

1993

[1]
O. Aichholzer and H. Hassler. A fast method for modulus reduction in residue number system. In Proc. epp'93, pages 41-54, Vienna, Austria, 1993. [IIG-Report-Series 312, TU Graz, Austria, 1991]. .

[2]
P. Auer. On-line learning of rectangles in noisy environments. In Proceedings of the Sixth Annual ACM Conference on Computational Learning Theory, pages 253-261. ACM Press, New York, NY, 1993.

[3]
P. Auer, P. M. Long, W. Maass, and G. J. Woeginger. On the complexity of function learning. In Proceedings of the 5th Annual ACM Conference on Computational Learning Theory, pages 392-401, 1993.

[4]
F. Aurenhammer. Geometric clustering and Voronoi-type partitions. In 16th IFIP Conf. System Modelling and Optimization, pages 93-94, Compiegne, France, 1993.

[5]
F. Aurenhammer. Voronoi diagrams -- a survey of a fundamental geometric data structure. bit acm computing surveys '91 (Japanese translation), Kyoritsu Shuppan Co., Ltd., pages 131-185, 1993.

[6]
M. Dietzfelbinger and W. Maass. The complexity of matrix transposition on one-tape off-line Turing machines with output tape. Theoretical Computer Science, 108:271-290, 1993. (PDF, 1496 KB).

[7]
A. Hajnal, W. Maass, P. Pudlak, M. Szegedy, and G. Turan. Threshold circuits of bounded depth. Journal of Computer and System Sciences, 46:129-154, 1993. (PDF, 1459 KB).

[8]
A. Hajnal, W. Maass, P. Pudlak, M. Szegedy, and G. Turan. Threshold circuits of bounded depth. J. Comput. System Sci., 46:129-154, 1993. (PDF, 1459 KB).

[9]
W. Maass. Bounds for the computational power and learning complexity of analog neural nets. In Proceedings of the 25th Annual ACM Symposium on Theory Computing, pages 335-344, 1993. (Gzipped PostScript, 2331 KB). (PDF, 1832 KB).

[10]
W. Maass, G. Schnitger, E. Szemeredi, and G. Turan. Two tapes versus one for off-line Turing machines. Computational Complexity, 3:392-401, 1993. (PDF, 617 KB).

[11]
B. Ruf. Sequentielle und parallele Lernverfahren fuer Boltzmann-Maschinen. Master's thesis, Rheinisch-Westfaelische Technische Hochschule Aachen, Germany, 1993. (in German). .

1992

[1]
O. Aichholzer. Hyperebenen in Hyperkuben - Eine Klassifizierung und Quantifizierung. Master's thesis, IGI-TU Graz, Austria, 1992. .

[2]
F. Aurenhammer and J. Hagauer. Computing equivalence classes among the edges of a graph with applications. Discrete Mathematics, 109:3-12, 1992. Special Issue. [IIG-Report-Series 271, TU Graz, Austria, 1989].

[3]
F. Aurenhammer, J. Hagauer, and W. Imrich. Cartesian graph factorization at logarithmic cost per edge. Computational Complexity, 2:331-349, 1992.

[4]
F. Aurenhammer, F. Hoffmann, and B. Aronov. Least-squares partitioning. In Proc. 8th European Workshop on Computational Geometry CG '92, pages 55-57, Utrecht, the Netherlands, 1992.

[5]
F. Aurenhammer, F. Hoffmann, and B. Aronov. Minkowski-type theorems and least-squares partitioning. In Proc. 8th Ann. ACM Symp. Computational Geometry, pages 350-357, Berlin, Germany, 1992. [Report B-92-09, FU Berlin, Germany, 1992].

[6]
F. Aurenhammer and O. Schwarzkopf. A simple on-line randomized incremental algorithm for computing higher order Voronoi diagrams. Int'l Journal of Computational Geometry & Applications, 2:363-381, 1992. Special Issue. [Report B 91-02, FU Berlin, Germany, 1991]. .

[7]
F. Aurenhammer and G. Stoeckl. Searching for segments with largest relative overlap. In Proc. 15th IFIP Conf. System Modelling and Optimization, Lecture Notes in Control and Information Sciences, volume 180, pages 77-84, Zuerich, Switzerland, 1992. Springer Verlag.

[8]
F. Aurenhammer and G. Stoeckl. Searching for segments with largest relative overlap. Information Processing Letters, 41:103-108, 1992. [Report B 91-10, FU Berlin, Germany, 1991].

[9]
Z. Chen and W. Maass. On-line learning of rectangles. In Proceedings of the 5th Annual ACM Workshop on Computational Learning Theory, pages 16-28, 1992. (PDF, 1169 KB).

[10]
Z. Chen and W. Maass. A solution of the credit assignment problem in the case of learning rectangles. In Proceedings of the 3rd Int. Workshop on Analogical and Inductive Inference, volume 642 of Lecture Notes in Artificial Intelligence, pages 26-34. Springer, 1992.

[11]
W. Maass and T. A. Slaman. The complexity types of computable sets. Journal of Computer and System Sciences, 44:168-192, 1992. Invited paper for a special issue of the J. Comput. Syst. Sci. (PDF, 1852 KB).

[12]
W. Maass and G. Turan. Lower bound methods and separation results for on-line learning models. Machine Learning, 9:107-145, 1992. Invited paper for a special issue of Machine Learning. (PDF, 1839 KB).

1991

[1]
P. Auer. Unification in the combination of disjoint theories. In Word Equations and Related Topics, pages 177-186. Lecture Notes of Computer Science 677, Springer, 1991.

[2]
P. Auer. Solving string equations with constant restrictions. In Word Equations and Related Topics, pages 103-132. Lecture Notes of Computer Science 677, Springer, 1991.

[3]
P. Auer, K. Hornik, and P. Révész. Some limit theorems for the homogeneous Poisson process. Statistics & Probability Letters, 12:91-96, 1991.

[4]
F. Aurenhammer. Using Gale transforms in computational geometry. Mathematical Programming, B 52:179-190, 1991. Special Issue. [IIG-Report-Series 248, TU Graz, Austria, 1988].

[5]
F. Aurenhammer. Voronoi diagrams -- a survey of a fundamental geometric data structure. ACM Computing Surveys, 23(3):345-405, 1991. Habilitationsschrift. [Report B 90-09, FU Berlin, Germany, 1990].

[6]
F. Aurenhammer and J. Hagauer. Recognizing binary Hamming graphs in O(n2 log n) time. In Proc. 16th Int'l Workshop on Graph-Theoretical Concepts in Computer Science, Lecture Notes in Computer Science, volume 484, pages 90-98, Berlin, Germany, 1991. Springer Verlag.

[7]
F. Aurenhammer and O. Schwarzkopf. A simple on-line randomized incremental algorithm for computing higher order Voronoi diagrams. In Proc. 7th Ann. ACM Symp. Computational Geometry, pages 142-151, North Conway, U.S.A., 1991.

[8]
F. Aurenhammer and G. Stoeckl. On the peeper's Voronoi diagram. SIGACT News, 22(4):50-59, 1991. [IIG-Report-Series 264, TU Graz, Austria, 1988]. .

[9]
F. Aurenhammer, G. Stoeckl, and E. Welzl. The post-office problem for fuzzy point sets. In Proc. 7th Workshop on Computational Geometry CG '91, Lecture Notes in Computer Science, volume 553, pages 1-11, Bern, Switzerland, 1991. Springer Verlag. [Report B 91-07, FU Berlin, Germany, 1991].

[10]
W. J. Bultman and W. Maass. Fast identification of geometric objects with membership queries. In Proceedings of the 4th Annual ACM Workshop on Computational Learning Theory,, pages 337-353, 1991.

[11]
M. Dietzfelbinger, W. Maass, and G. Schnitger. The complexity of matrix transposition on one-tape off-line Turing machines. Theoretical Computer Science, 82:113-129, 1991. (PDF, 1103 KB).

[12]
A. Gupta and W. Maass. A method for the efficient design of Boltzmann machines for classification problems. In Advances in Neural Information Processing Systems, R. P. Lippmann, J. E. Moody, and D. S. Touretzky, editors, volume 3, pages 825-831. Morgan Kaufmann, (San Mateo), 1991. (PDF, 513 KB).

[13]
W. Maass. On-line learning with an oblivious environment and the power of randomization. In Proceedings of the 4th Annual ACM Workshop on Computational Learning Theory, pages 167-175. Morgan Kaufmann (San Mateo), 1991. (PDF, 786 KB).

[14]
W. Maass, G. Schnitger, and E. Sontag. On the computational power of sigmoid versus boolean threshold circuits. In Proc. of the 32nd Annual IEEE Symposium on Foundations of Computer Science 1991, pages 767-776, 1991. (PDF, 810 KB).

[15]
W. Maass and T. A. Slaman. Splitting and density for the recursive sets of a fixed time complexity. In Proceedings of a Workshop on Logic from Computer Science, Y. N. Moschovakis, editor, pages 359-372. Springer (Berlin), 1991. (PDF, 814 KB).

1990

[1]
P. Auer. The circle homogeneously covered by random walk on Z2. Statistics & Probability Letters, 9:403-407, 1990.

[2]
F. Aurenhammer. A new duality result concerning Voronoi diagrams. Discrete & Computational Geometry, 5(3):243-254, 1990. [IIG-Report-Series 216, TU Graz, Austria, 1985].

[3]
F. Aurenhammer. A relationship between Gale transforms and Voronoi diagrams. Discrete Applied Mathematics, 28:83-91, 1990. [IIG-Report-Series 247, TU Graz, Austria, 1988].

[4]
F. Aurenhammer, J. Hagauer, and W. Imrich. Factoring Cartesian-product graphs at logarithmic cost per edge. In Proc. MPS Conf. Integer Programming and Combinatorial Optimization IPCO'90, pages 29-44, Waterloo, Canada, 1990. [IIG-Report-Series 287, TU Graz, Austria, 1990].

[5]
F. Aurenhammer and G. Stoeckl. Fenster - Voronoi Diagramme (Abstract). In Tagungsband DMV Jubilaeumstagung, page 52, Bremen, Germany, 1990.

[6]
W. Maass and T. A. Slaman. On the relationship between the complexity, the degree, and the extension of a computable set. In Proceedings of the 1989 Recursion Theory Week Oberwolfach, pages 297-322. Springer (Berlin), 1990. (PDF, 1967 KB).

[7]
W. Maass and G. Turan. On the complexity of learning from counterexamples and membership queries. In Proceedings of the 31th Annual IEEE Symposium on Foundations of Computer Science, pages 203-210, 1990. (PDF, 650 KB).



A full list of publications done by members of the IGI is also available.