Seminar Computational Intelligence A (708.111)

WS 2014

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/


Assoc. Prof. Dr. Robert Legenstein

Office hours: by appointment (via e-mail)

E-mail: robert.legenstein@igi.tugraz.at
Homepage: www.igi.tugraz.at/legi/




Location: IGI-seminar room, Inffeldgasse 16b/I, 8010 Graz
Date: starting from October 6th  2014, every Monday, 16:15 - 18:00 p.m.
Zeugnis: Ein Vortrag in diesem Seminar kann auch als Zeugnis für ein anders Seminar des Institutes angerechnet werden.
(Credits: A talk in this seminar can also be used to take formal credits for other seminars of the institute.)


Content of the seminar: Cognitive Computing

IBM and other major companies propose that we are entering a new age of computing and computer use. It is characteristic for this new age, that machines take over many cognitive processes of humans, and interact in novel ways with humans. In addition, the design of new energy efficient computer hardware moves towards brain inspired circuit designs and computing paradigms. The students will present in this seminar recent reports and overviews of these new developments (length of talks: 30 min).

Talks:

This is a tentative schedule!
Date
Speaker Paper

Nov 10

Loigge Stefan


Smart Machines PDF
SLIDES

Nov 10

Lassnig Konstantin

Smart Machines PDF
SLIDES

Dec 1

Karl Anja


Building Watson: An overview of the DeepQA project (PDF) or Introduction to ''This is Watson'' (PDF).
SLIDES

Dec 1

Donsa Klaus

Watson: Beyond Jeopardy! PDF
SLIDES

Dec 15

Imlauer Stefan


A million spiking-neuron integrated circuit with a scalable communication network and interface. PDF
SLIDES

Dec 15

Haubenwallner Karl


Spike-Based Convolutional Network for Real-Time Processing PDF
SLIDES

Jan 12

Subramoney Anand


Biological aspects of "Performance-optimized hierarchical models predict neural responses in higher visual cortex." PDF

Jan 12

Haas Sarah


Verification/Testing in "Performance-optimized hierarchical models predict neural responses in higher visual cortex." PDF

Jan 19

Feichtenhofer Christoph


Convolutional Neural Networks.
SLIDES

Jan 19

Schanner Gabriel



Network model used in "Performance-optimized hierarchical models predict neural responses in higher visual cortex." PDF
SLIDES

Jan 21

Vodopivec Tadej


Self-superwised monocular road detection in desert terrain. PDF

Jan 21

Limbacher Thomas

SLIDES

Emergence of dynamic memory traces in cortical microcircuit models through STDP PDF
SLIDES




Notes on talk material:

  • Smart Machines: IBM's Watson and the Era of Cognitive Computing, Columbia Univ. Press 2013.
    PDF (login: lehre password: ask anyone in our Institute, or send email to us).
    • Talk 1: The main points from Ch. 1 and 2
    • Talk 2: The main points from ch. 5 and 6
    (Notes: these talks are technically very easy, and should be given right at the beginning of the seminar, e.g. on Oct. 20 or 27)

  • Ferrucci, D., Brown, E., Chu-Carroll, J., Fan, J., Gondek, D., Kalyanpur, A. A., ... & Welty, C. (2010). Building Watson: An overview of the DeepQA project. AI Magazine, 31(3), 59-79.
    PDF

  • Ferrucci, D., Levas, A., Bagchi, S., Gondek, D., & Mueller, E. T. (2013). Watson: Beyond Jeopardy!. Artificial Intelligence, 199, 93-105.
    PDF

  • Merolla, P. A., Arthur, J. V., Alvarez-Icaza, R., Cassidy, A. S., Sawada, J., Akopyan, F., ... & Modha, D. S. (2014). A million spiking-neuron integrated circuit with a scalable communication network and interface. Science, 345(6197), 668-673.
    PDF
    (combine with commentary: R.F. Servive: The brain chip, Science 2014, p. 614-616)

  • Yamins, D. L., Hong, H., Cadieu, C. F., Solomon, E. A., Seibert, D., & DiCarlo, J. J. (2014). Performance-optimized hierarchical models predict neural responses in higher visual cortex. Proceedings of the National Academy of Sciences, 201403112.
    PDF
    This remarkable new publication from the DiCarlo Lab at MIT analyzes for the first time simultaneously the object recognition performance of a deep learning model for object recognition, and its relation to recordings from neurons in higher visual areas of the brain during visual object recognition. The results are truly remarkable, and provide insight into both brain inspired models for vision and visual processing in the brain.
    (could provide material for up to 3 talks, including the content of the supplement of the paper)