Goto

Collaborating Authors

 Industry






A grandmaster chess machine

Classics

scientificamerican1090-44.pdf http://www.nature.com/scientificamerican/journal/v263/n4/pdf  -- requires permission Scientific American, 263 (4), 4-50.



An Optimality Principle for Unsupervised Learning

Neural Information Processing Systems

We propose an optimality principle for training an unsupervised feedforward neural network based upon maximal ability to reconstruct the input data from the network outputs. We describe an algorithm which can be used to train either linear or nonlinear networks with certain types of nonlinearity. Examples of applications to the problems of image coding, feature detection, and analysis of randomdot stereograms are presented.


A Computationally Robust Anatomical Model for Retinal Directional Selectivity

Neural Information Processing Systems

We analyze a mathematical model for retinal directionally selective cells based on recent electrophysiological data, and show that its computation of motion direction is robust against noise and speed.


Theory of Self-Organization of Cortical Maps

Neural Information Processing Systems

We have mathematically shown that cortical maps in the primary sensory cortices can be reproduced by using three hypotheses which have physiological basis and meaning. Here, our main focus is on ocular.dominance


Neural Networks for Model Matching and Perceptual Organization

Neural Information Processing Systems

We introduce an optimization approach for solving problems in computer vision that involve multiple levels of abstraction. Our objective functions include compositional and specialization hierarchies. We cast vision problems as inexact graph matching problems, formulate graph matching in terms of constrained optimization, and use analog neural networks to perform the optimization. The method is applicable to perceptual grouping and model matching. Preliminary experimental results are shown.