Neural Networks for Vision, Speech and Natural Language
Published on 6. December 2012
XII, 442 pages
978-94-011-2360-0 (ISBN)
Description
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.
Reviews / Votes
`... admirably clearly written, and well structured throughout...The book succeeds very well in its aims: it does improve on the weaknesses of comparisons between approaches in the literature; it implicitly sets out how industrially oriented research is best carried out; and it presents some interesting, sometimes fascinating new results and approaches.'Network 3
`This volume collects the more successful case studies from a very large research project at BT Laboratories that set out to investigate the applicability of neural computing to speech, vision and the natural language problems in this application context...of interest to researchers with specialist knowledge of these subjects or, especially, to those with an interest in the application of multi-layer perceptions to practical problems.'
Computing
More details
Other editions
Additional editions
R. Linggard | D.J. Myers | C. Nightingale
Neural Networks for Vision, Speech and Natural Language
Book
11/2012
Springer
€106.99
Shipment within 15-20 days
R. Linggard | D.J. Myers | C. Nightingale
Neural Networks for Vision, Speech and Natural Language
Book
03/1992
1st Edition
Chapman and Hall
€115.50
Article exhausted; check different version
Content
Introduction: neural networks for vision, speech and natural language.- Introduction: neural networks for vision, speech and natural language.- 1 Vision.- Neural networks for vision: an introduction.- 1 Image feature location in multi-resolution images using a hierarchy of multilayer perceptrons.- 2 Training multilayer perceptrons for facial feature location: a case study.- 3 The detection of eyes in facial images using radial basis functions.- 4 A neural network feature detector using a multi-resolution pyramid.- 5 Training and testing of neural net window operators on spatiotemporal image sequences.- 6 Image classification using Gabor representations with a neural net.- 2 Speech.- Neural networks for speech processing: an introduction.- 7 Spoken alphabet recognition using multilayer perceptrons.- 8 Speaker independent vowel recognition.- 9 Dissection of perceptron structures in speech and speaker recognition.- 10 Segmental sub-word unit classification using a multilayer perceptron.- 3 Natural Language.- Connectionist natural language processing: an introduction.- 11 A single layer higher order neural net and its applications to context free grammar recognition.- 12 Functional compositionality and soft preference rules.- 13 Applications of multilayer perceptrons in text-to-speech synthesis systems.- 4 Implementation.- Hardware implementation of neural networks: an introduction.- 14 Finite wordlength, integer arithmetic multilayer perceptron modelling for hardware realization.- 15 A VSLI architecture for implementing neural networks with on-chip backpropagation learning.- 16 An opto-electronic neural network processor.- 5 Architectures.- Architectures: an introduction.- 17 A dynamic topology net.- 18 The stochastic search network.- 19 Node sequence networks.- 20 Some dynamical properties of neural networks.
