An automaton framework for neural nets that learn

Brindley (1967, 1969, 1972) has discussed nets of several types of formal neurons, many of whose functions are modifiable by their own input stimuli. Because Brindley's results are widely referred to, for example Marr (1970, 1971) and include some of the scarce non-trivial theorems on learning nets, it is important that serious side-conditions be made explicit. The language of finite automata is used to mathematicize the problem of adaptation sufficiently to remove some ambiguities of Brindley's approach. We close the paper by relating our framework to other formal studies of adaptation.

[1]  T J Teyler,et al.  The neurophysiology of learning. , 1972, Annual review of psychology.

[2]  G. Brindley.  The classification of modifiable synapses and their use in models for conditioning , 1967, Proceedings of the Royal Society of London. Series B. Biological Sciences.

[3]  D. Marr.  A theory for cerebral neocortex , 1970, Proceedings of the Royal Society of London. Series B. Biological Sciences.

[4]  M. Arbib.  Memory limitations of stimulus-response models. , 1969 .

[5]  Robert Rosen,et al.  Chapter 4 – SOME RELATIONAL CELL MODELS: THE METABOLISM-REPAIR SYSTEMS , 1972 .

[6]  Michael Abib.  Categories of (ℓ, ℛ)-systems , 1966 .

[7]  D Marr,et al.  Simple memory: a theory for archicortex. , 1971, Philosophical transactions of the Royal Society of London. Series B, Biological sciences.

[8]  G S Brindley,et al.  Nerve net models of plausible size that perform many simple learning tasks , 1969, Proceedings of the Royal Society of London. Series B. Biological Sciences.

[9]  Brian R. Gaines,et al.  Axioms for adaptive behaviour , 1972 .