Artigo Revisado por pares

Theory of the backpropagation neural network

1988; Elsevier BV; Volume: 1; Linguagem: Inglês

10.1016/0893-6080(88)90469-8

ISSN

1879-2782

Autores

Robert Hecht-Nielsen,

Tópico(s)

Advanced Memory and Neural Computing

Resumo

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.

Referência(s)
Altmetric
PlumX