From the Publisher:
An Introduction to Nueral Networks will be warmly welcomed by a wide readership seeking an authoritative treatment of this key subject without an intimidating level of mathematics in the presentation.

An introduction to neural networks

Publisher Summary This chapter presents a survey of the elementary theory of the basic backpropagation neural network architecture, covering the areas of architectural design, performance measurement, function approximation capability, and learning. The survey includes a formulation of the backpropagation neural network architecture to make it a valid neural network and a proof that the backpropagation mean squared error function exists and is differentiable. Also included in the survey is a theorem showing that any L2 function can be implemented to any desired degree of accuracy with a three-layer backpropagation neural network. An appendix presents a speculative neurophysiological model illustrating the way in which the backpropagation neural network architecture might plausibly be implemented in the mammalian brain for corticocortical learning between nearby regions of cerebral cortex. One of the crucial decisions in the design of the backpropagation architecture is the selection of a sigmoidal activation function.

Theory of the backpropagation neural network

The author presents a survey of the basic theory of the backpropagation neural network architecture covering architectural design, performance measurement, function approximation capability, and learning. The survey includes previously known material, as well as some new results, namely, a formulation of the backpropagation neural network architecture to make it a valid neural network (past formulations violated the locality of processing restriction) and a proof that the backpropagation mean-squared-error function exists and is differentiable. Also included is a theorem showing that any L/sub 2/ function from (0, 1)/sup n/ to R/sup m/ can be implemented to any desired degree of accuracy with a three-layer backpropagation neural network. The author presents a speculative neurophysiological model illustrating how the backpropagation neural network architecture might plausibly be implemented in the mammalian brain for corticocortical learning between nearby regions of the cerebral cortex. >

Sparse coding of sensory inputs.

https://www.cell.com/trends/neurosciences/pdf/0166-2236(87)90011-7.pdf

Hippocampal synaptic enhancement and information storage within a distributed memory system

The features of a hologram that commend it as a model of associative memory can be improved on by other devices.

Non-holographic associative memory

The problem of how the brain stores and retrieves information is ultimately an experimental one, and its solution will doubtless call for the combined resources of psychology, physiology and molecular biology. But it is also a problem of great theoretical sophistication; and one of the major tasks confronting the brain scientist is the construction of theoretical models which are worthy of, and open to, experimental test. In this review we shall be concerned with the latter aspect of the problem of memory, which has attracted quite a lot of attention in the last few years. It is early yet to judge the relative merits of the various models in any detail; but as we shall see, most of those which have been developed beyond their initial hypotheses have a certain family resemblance, and it seems as if we may now be in possession of the basic ideas which will be needed for the understanding of one of the central problems of memory, namely the mechanism of associative recall.

O. P. Buneman

Papers

Non-holographic associative memory

Theories of associative recall.