Seminar Computational Intelligence E (708.115)

SS 2010

Institut für Grundlagen der Informationsverarbeitung (708)
 

Lecturer: O.Univ.-Prof. Dr. Wolfgang Maass

Office hours: by appointment (via e-mail)

E-mail: maass@igi.tugraz.at
Homepage: www.igi.tugraz.at/maass/



Location: IGI-seminar room, Inffeldgasse 16b/I, 8010 Graz
Date: Wednesday, 4.15 pm
starting on March 10th, 2010


Content of the seminar:

New Research Results in Probabilistic Inference, with applications in Computer Science, Robotics,  and Cognitive Science. In addition a few new research results from neuroscience are discussed that are relevant for our research.


Talks:

Mi 21.4.

Klaus Schuch:

Decorrelated neuronal firing in cortical microcircuits.Ecker AS, Berens P, Keliris GA, Bethge M, Logothetis NK, Tolias AS. Science. 2010 Jan 29;327(5965):584-7.  IGI-pdf-archive

Presentation: PDF

 

Gregor Hörzer:  TBA

Interactions of neural populations in visual and prefrontal areas during visual short-term memory

(overview of the results of the research collaboration with the MPI for Biological Cybernetics in Tuebingen)

 


Do 22.4.

Videolectures by Zoubin Ghahramani and Josh Tenenbaum on
Graphical Models and their Applications in Cognitive Science
http://videolectures.net/mlss09uk_ghahramani_gm/
http://videolectures.net/mlss09uk_tenenbaum_mlcs/
Lecture Material:
http://velblod.videolectures.net/2009/pascal2/mlss09uk_cambridge/ghahramani_gm/mlss09uk_ghahramani_gm.pdf
http://velblod.videolectures.net/2009/pascal2/mlss09uk_cambridge/tenenbaum_mlcs/mlss09uk_tenenbaum_mlcs_01.pdf



Mi 28.4.

Johannes Bill (covering basic concepts of sampling from ch. 11 in the book by C. Bishop)

Presentation: PDF

and Dejan Pecevski (ch. 3 of the following thesis):
Mansinghka. Natively Probabilistic Computation. PhD Dissertation, 2009. [2009 George M. Sprowls Award for best doctoral thesis at MIT  in computer science.]
http://web.mit.edu/vkm/www/vkm-dissertation.pdf

Presentation: PDF



Do 29.4.
Elmar Rückert and Gerhard Neumann:
Basic paradigms for applications of probabilistic inference in robotics, based on the following review paper, as well as other papers and own ideas):
Marc Toussaint (2009): Probabilistic inference as a model of planned behavior.
Künstliche Intelligenz (German Artificial Intelligence Journal) volume 3/09
http://user.cs.tu-berlin.de/~mtoussai/publications/09-toussaint-survey.pdf
(very nice introduction into use of graphical models for motor control and planning; but sections of this paper should be combined with more detailed material from one of the paper below for a good talk)

Presentations: Part I, Part II



Mi 5.5.

Werner Bailer:
V Savova, F Jäkel, JB Tenenbaum - Grammar-based object representations in a scene parsing task (2008)
http://141.14.165.6/CogSci09/papers/150/paper150.pdf
Presentation: PDF

Stefan Klampfl :

B Kappen, V Gomez, M Opper
Optimal control as a graphical model inference problem
http://arxiv.org/PS_cache/arxiv/pdf/0901/0901.0633v2.pdf

Presentation: PDF

 


Mi 9.6.

Stefan Habenschuss:

N Vlassis, M Toussaint, G Kontes, S Piperidis
Learning model-free robot control by a Monte Carlo EM algorithm
Autonomous Robots, 2009
http://user.cs.tu-berlin.de/~mtoussai/publications/09-vlassis-et-al-auro.pdf

Presentation: PDF

 

Helmut Puhr:

Training products of experts by minimizing contrastive divergence
GE Hinton - Neural Computation, 2002
http://www.csri.utoronto.ca/~hinton/absps/nccd.pdf
(see also short sketch on
http://www.robots.ox.ac.uk/~ojw/files/NotesOnCD.pdf

Presentation: PDF



Do 10.6.

Gernot Griesbacher:
Vul, E., Goodman, N.D., Griffiths, T.L. & Tenenbaum, J.B. (2009) "One and Done? Optimal decisions from very few samples." 31st Annual Meeting of the Cognitive Science Society.
http://www.edvul.com/pdf/VulGoodmanGriffithsTenenbaum-cogsci-2009.pdf

Presentation: PDF

 

Georg Krempl:
Nikos Vlassis, Marc Toussaint (2009): Model-Free Reinforcement Learning as Mixture Learning. 25nd International Conference on Machine Learning (ICML 2009).
http://user.cs.tu-berlin.de/~mtoussai/publications/09-vlassis-toussaint-ICML.pdf
Presentation: PDF



Mi 16.6.
Elmar Rückert and Matthias Zöhrer:
Levy, R., Reali, F., & Griffths, T. L. (2009). Modeling the effects of memory on human online sentence processing with particle filters. Advances in Neural Information Processing Systems 21
http://cocosci.berkeley.edu/tom/papers/sentencepf1.pdf

Presentations: Part I, Part II



Do 17.6.

Stefan Haeusler and David Kappel:
A probabilistic model of theory formation
C Kemp, JB Tenenbaum, S Niyogi, TL Griffiths - Cognition, 2009
http://www.psy.cmu.edu/~ckemp/papers/kemptng09.pdf 

Presentations: Part I, Part II

 

Mi 23.6.
Jing Fang (until p.5, middle); Alex Kreilinger:

N.T. Markov; unpublished results on the graph structure of cortical networks, IGI-pdf-archive

Presentations: Part I, Part II



Do 24.6.

Christian Breitwieser :

(same paper as previous day)

Presentation: PDF

 

Robert Legenstein:

P. J. Sjöström, E. A. Rancz, A. Roth, and M. Häusser. Dendritic excitability and synaptic plasticity. Physiol. Rev., 88:769-840, 2008

Presentation: PDF

 

 

Mi 30.6. 

(begin at 15:15)
Bernhard Nessler,  Lars Büsing,  Christoph Zechner:
Selected parts of
VARIATIONAL ALGORITHMS FOR APPROXIMATE BAYESIAN INFERENCE by Matthew J. Beal (Phd thesis, Gatsby-London, 2003)
http://www-sigproc.eng.cam.ac.uk/~ej230/bib/bayesian/beal03.pdf
(and possibly from other sources)
Presentations: Part I, Part II, Part III


(possibly further talks)