In unsupervised learning, the realisation that simple neural network architectures ar Documents: Advanced Search Include Citations. Venue: Biological Cybernetics Citations: 17 - 8 self.
Buy eBook. Buy Hardcover.
Buy Softcover. FAQ Policy.
Show all. From the reviews of the first edition: "This book is concerned with developing unsupervised learning procedures and building self organizing network modules that can capture regularities of the environment. Table of contents 15 chapters Table of contents 15 chapters Introduction Pages Background Pages The Negative Feedback Network Pages Peer-Inhibitory Neurons Pages Multiple Cause Data Pages The negative feedback circumvents the well-known difficulty of positive feedback in Hebbian learning systems which causes the networks' weights to increase without bound.
We show, both analytically and experimentally, that not only do the weights of networks with this architecture converge, they do so to values which give the networks important information processing properties: linear versions of the model are shown to perform a Principal Component Analysis of the input data while a non-linear version is shown to be capable of Exploratory Projection Pursuit. While there is no claim that the networks described herein represent the complexity found in biological networks, we believe that the networks investigated are not incompatible with known neurobiology.
However, the main thrust of the thesis is a mathematical analysis of the emergent properties of the network; such analysis is backed by empirical evidence at all times.