This book is a collection of chapters describing work carried out as part of a large project at BT Laboratories to study the application of connectionist methods to problems in vision, speech and natural language processing. Also, since the theoretical formulation and the hardware realization of neural networks are significant tasks in themselves, these problems too were addressed. The book, therefore, is divided into five Parts, reporting results in vision, speech, natural language, hardware implementation and network architectures. The three editors of this book have, at one time or another, been involved in planning and running the connectionist project. From the outset, we were concerned to involve the academic community as widely as possible, and consequently, in its first year, over thirty university research groups were funded for small scale studies on the various topics. Co-ordinating such a widely spread project was no small task, and in order to concentrate minds and resources, sets of test problems were devised which were typical of the application areas and were difficult enough to be worthy of study. These are described in the text, and constitute one of the successes of the project.

This text is written by researchers at BT Laboratories and at universities who have investigated a set of problems in vision, speech and natural language. It presents a diversity of approaches to the solution of these problems, based on a range of neural network paradigms. The book also includes sections on implementation, which discuss some approaches to hardware realization; and architectures, which describe new ideas and algorithms. The findings discussed here should be of interest not only to those working in the applications areas discussed, but also to people working more widely in the field of neural networks. This book should be of interest to working researchers and graduate students in neural networks.