The choice of transfer functions may strongly influence complexity and performance of
neural networks. Although sigmoidal transfer functions are the most common there is no a …

Sigmoidal or radial transfer functions do not guarantee the best generalization nor fast
learning of neural networks. Families of parameterized transfer functions provide flexible …

Many feedforward neural network architectures have the property that their overall input-
output function is unchanged by certain weight permutations and sign flips. In this paper, the …

There is presently great interest in the abilities of neural networks to mimic" qualitative
reasoning" by manipulating neural incodings of symbols. Less work has been performed on …

A variety of algorithms already known to the neural networks community have, thus far, not
seen widespread acceptance among developers. Masters presents these algorithms and …

A comprehensive review on the problem of choosing a suitable activation function for the
hidden layer of a feed forward neural network has been widely investigated. Since the …

INTRODUCTION TO THE THEORY OF NEURAL COMPUTATION Page 1 Page 2
INTRODUCTION TO THE THEORY OF NEURAL COMPUTATION Page 3 Page 4 …

Neural network models are currently being considered for a wide variety of important
computational tasks, particularly those involving imprecise inputs. This paper suggests …

A modification of the generalized delta rule is described that is capable of training multilayer
networks of value units, ie units defined by a particular non-monotonic activation function …

We describe a method of constructing higher-order neural networks that respond invariantly
under geometric transformations on the input space. By requiring each unit to satisfy a set of …