Modeling neural networks in Scheme

A system for simulating neural networks has been written in the LISP dialect, Scheme, using an object-oriented style of program ming, rather than the standard numerical techniques used in previous studies. Each node in the Scheme network represents either a neuron or a functional group of neurons, and can pass messages which trigger computations and actions in other nodes. The Scheme modeling approach overcomes two major problems inherent to the standard numerical approach. First, it provides a flexible environment for systematically studying the effects of perturbing a network's structure, response, or updating param eters. In fact, the Scheme system can recreate any previously studied neural network. Second, it allows the construction of hierarchical networks with several interacting levels. This system can handle hierarchical organization in a natural way, because a single node in a Scheme network can contain a model of an entire lower level of neural processing. The implementation of neural networks with hierarchical structure is significant because recent biological data suggests that this is the architecture which supports human cognition.

[1]  M. Jouvet,et al.  The states of sleep. , 1967, Scientific American.

[2]  S. Grossberg How does a brain build a cognitive code , 1980 .

[3]  J. Szentágothai The Ferrier Lecture, 1977 The neuron network of the cerebral cortex: a functional interpretation , 1978, Proceedings of the Royal Society of London. Series B. Biological Sciences.

[4]  Alan E. Gelfand A behavioral summary for completely random nets , 1982 .

[5]  D. Kahneman,et al.  Attention and Effort , 1973 .

[6]  W. A. Little,et al.  Analytic study of the memory storage capacity of a neural network , 1978 .

[7]  M. Mishkin A memory system in the monkey. , 1982, Philosophical transactions of the Royal Society of London. Series B, Biological sciences.

[8]  S. Grossberg,et al.  How does a brain build a cognitive code? , 1980, Psychological review.

[9]  S. Kauffman Metabolic stability and epigenesis in randomly constructed genetic nets. , 1969, Journal of theoretical biology.

[10]  R. A. Sherlock Analysis of the behaviour of Kauffman binary networks—I. State space description and the distribution of limit cycle lengths , 1979 .

[11]  J. Holland Cycles in logical nets , 1960 .

[12]  Stephen Grossberg,et al.  A Theory of Human Memory: Self-Organization and Performance of Sensory-Motor Codes, Maps, and Plans , 1982 .

[13]  Stephen A. Ritz,et al.  Distinctive features, categorical perception, and probability learning: some applications of a neural model , 1977 .

[14]  J J Hopfield,et al.  Neural networks and physical systems with emergent collective computational abilities. , 1982, Proceedings of the National Academy of Sciences of the United States of America.

[15]  S. Amari,et al.  Competition and Cooperation in Neural Nets , 1982 .

[16]  W Singer,et al.  Control of thalamic transmission by corticofugal and ascending reticular pathways in the visual system. , 1977, Physiological reviews.