A method is described for designing by computer a binary decision tree that, using the coefficients determined by the learning process, would speed up the classification of patterns.

A method is described for designing by computer a binary decision tree that, using the coefficients determined by the learning process, would speed up the classification of patterns.

Character and handwriting recognition by computers is attracting much attention particularly because of its potential for application in many areas such as office automation, bank check processing, recognition of postal addresses and ZIP Codes, signature verification, and document and text recognition.Over the past four decades, many methods have been proposed, developed and tested for computers to recognize characters, and they have been reported in a variety of publications. The present volume is a coherent and integrated publication containing papers which give new research results in this increasingly active field. It is a boon to researchers, scientists and engineers who need to keep abreast of new developments in character and handwriting methodologies and applications.

Neural computation arises from the capacity of nervous tissue to process information and accumulate knowledge in an intelligent manner. Conventional computational machines have encountered enormous difficulties in duplicatingsuch functionalities. This has given rise to the development of Artificial Neural Networks where computation is distributed over a great number of local processing elements with a high degree of connectivityand in which external programming is replaced with supervised and unsupervised learning. The papers presented in this volume are carefully reviewed versions of the talks delivered at the International Workshop on Artificial Neural Networks (IWANN '93) organized by the Universities of Catalonia and the Spanish Open University at Madrid and held at Barcelona, Spain, in June 1993. The 111 papers are organized in seven sections: biological perspectives, mathematical models, learning, self-organizing networks, neural software, hardware implementation, and applications (in five subsections: signal processing and pattern recognition, communications, artificial vision, control and robotics, and other applications).