One may argue that the simplest type of neural networks beyond a single perceptron is an array of several perceptrons in parallel. In spite of their simplicity, such circuits can compute any Boolean function if one views the majority of the binary perceptron outputs as the binary output of the parallel perceptron, and they are universal approximators for arbitrary continuous functions with valu...

We introduce a new algorithm designed to learn sparse perceptrons over input representations which include high-order features. Our algorithm, which is based on a hypothesis-boosting method, is able to PAC-learn a relatively natural class of target concepts. Moreover, the algorithm appears to work well in practice: on a set of three problem domains, the algorithm produces classifiers that utili...

Parallel perceptrons (PPs), a novel approach to committee machine training requiring minimal communication between outputs and hidden units, allows the construction of efficient and stable nonlinear classifiers. In this work we shall explore how to improve their performance allowing their output weights to have real values, computed by applying Fisher’s linear discriminant analysis to the commi...

More than forty years have passed since a learning machine called the perceptron was proposed by Rosenblatt. It has played a major role for these forty years, not only in the area of computational neuroscience in elucidating the function of cerebellum, but also in theoretical and practical studies of learning machines. The present talk reviews these developments from my personal point

Multilayer Perceptrons and trained classification trees are two very different techniques which have recently become popular. Given enough data and time, both methods are capable of performing arbitrary nonlinear classification. We first consider the important differences between multilayer Perceptrons and classification trees and conclude that there is not enough theoretical basis for the clea...

In some real world situations, linear models are not sufficient to represent accurately complex relations between input variables and output variables of a studied system. Multilayer Perceptrons are one of the most successful non-linear regression tool but they are unfortunately restricted to inputs and outputs that belong to a normed vector space. In this chapter, we propose a general recoding...

Multi-layer perceptrons are often slow to learn nonlinear functions with complex local structure due to the global nature of their function approximations. It is shown that standard multi-layer perceptrons are actually a special case of a more general network formulation that incorporates B-splines into the node computations. This allows novel spline network architectures to be developed that c...

In this article we discuss our approach to the evolution of wandering behavior in a multi agent system (MAS). Our discussion covers the various aspects of the system setup, the performed experiments and the interpretation of the results observed. Utilizing a genetic algorithm (GA) and multi layer perceptrons (ANN) we show how wandering behavior is developed provided a single fitness criterion. ...