Matthew Cook

Position:

Company: INI

Research interest:

How does thinking work? How does the cortex compute? This is one of today's greatest mysteries in science. We do not yet know how to make machines do computations similar to the computations done with ease by animal brains. By experimenting with cortically inspired architectures, we hope to gain an understanding of how such computation can occur. One of our current directions is examining models similar to belief propagation on factor graphs, and how such models can be adapted to naturally solve learning and control problems of the sort that brain solves naturally.

External Link:
E-mail: cook@ini.phys.ethz.ch
Phone: 41 44 635 3097
Fax:

Mailing Address:
Institute of Neuroinformatics
Winterthurerstrasse 190
8057 - Zurich
Switzerland

Workpackages :

Foundation assembly

Publications :

Cook M, Jug F, Krautz C - Neuronal Projections Can Be Sharpened by a Biologically Plausible Learning Mechanism (2011), ICANN 2011, Lecture Notes in omputer science 6791: 101-08

Zubler F, Hauri A, Pfister S, Cook M, Douglas RJ - An instruction language for self-construction in the context of neural networks (2011), Frontiers in Computer Neuroscience 5(57)

Cook M, Jug F, Krautz C, Steger A - Unsupervised Learning of Relations (2010), International Conference on Artificial Neural Networks (1), pp. 164-173

Cook M, Jug F, Krautz C - Sharpening Projections: Inter-Area projections can be effectively sharpened by biologically plausible learning mechanisms (2009), CNS

Goehlsdorf D, Zubler F, Cook M - Robust simulation of cell-interactions using three-dimensional Delaunay triangulations (2008), FENS Forum poster presentation

Goehlsdorf D, Zubler F, Cook M - Robust simulation of cell-interactions using three-dimensional Delaunay triangulations (2008), ZNZ Symposium

Cook M, Rothemund PW, Winfree E - Self-assembled circuit patterns (2004), LNCS : DNA Computers 9 : 91-107

Back

Print