Bøker i Developments in Connectionist Theory Series-serien

First Published in 1991. Routledge is an imprint of Taylor & Francis, an informa company.

Composed of three sections, this book presents the training algorithm for neural networks: backpropagation. The first presents the theory and principles; the second a number of network architectures; and the third shows how these can be applied to a number of different fields.

Composed of three sections, this book presents the training algorithm for neural networks: backpropagation. The first presents the theory and principles; the second a number of network architectures; and the third shows how these can be applied to a number of different fields.

A body of results of new mathematical learning and processing in neural networks. The book also fills in background in such areas as computability theory, theory of analogue computation, time-series analysis, Bayesian analysis, computational learning theory and mathematical statistics.

Written for cognitive scientists, psychologists, computer scientists, engineers, and neuroscientists, this book provides an accessible overview of how computational network models are being used to model neurobiological phenomena.

First Published in 1991. Routledge is an imprint of Taylor & Francis, an informa company.