C++ Neural Networks and Fuzzy Logic: Preface

C++ Neural Networks and Fuzzy Logic

by Valluru B. Rao

MTBooks, IDG Books Worldwide, Inc.

ISBN: 1558515526   Pub Date: 06/01/95

Previous Table of Contents Next

Instar and Outstar

Outstar and instar are terms defined by Stephen Grossberg for ways of looking at neurons in a network. A

neuron in a web of other neurons receives a large number of inputs from outside the neuron’s boundaries. This

is like an inwardly radiating star, hence, the term instar. Also, a neuron may be sending its output to many

other destinations in the network. In this way it is acting as an outstar. Every neuron is thus simultaneously

both an instar and an outstar. As an instar it receives stimuli from other parts of the network or from outside

the network. Note that the neurons in the input layer of a network primarily have connections away from them

to the neurons in the next layer, and thus behave mostly as outstars. Neurons in the output layer have many

connections coming to it and thus behave mostly as instars. A neural network performs its work through the

constant interaction of instars and outstars.

A layer of instars can constitute a competitive layer in a network. An outstar can also be described as a source

node with some associated sink nodes that the source feeds to. Grossberg identifies the source input with a

conditioned stimulus and the sink inputs with unconditioned stimuli. Robert Hecht−Nielsen’s

Counterpropagation network is a model built with instars and outstars.