BOOK Fiesler-96.1/IDIAP Handbook of Neural Computation Fiesler, Emile Ed. Beale, R. Ed. adalaine adaptive resonance theory application artificial neural network associative memory backpropagation bidirectional associative memory case study combinatorial optimization connectionism connectionist network control data compression feedback network feedforward network functional-link network fundamentals fuzzy-neural system hardware implementation Hopfield network hybrid system image processing LVQ madalaine modelling of cognitive phenomena multilayer perceptron neocognitron network analysis neural computation neural computing neural expert system neural network neural-evolutionary system ontogenic neural network pattern classification perceptron prediction radial basis function recurrent neural network self-organizing feature map signal processing software implementation supervised learning time series analysis topology training unsupervised learning The Computational Intelligence Library 1996 Institute of Physics and Oxford University Press New York, New York The electronic version is expected in early 1997. 0-7503-0312--3 and 0-7503-0413-8 Many scientists and engineers now use neural networks to tackle problems that are either intractable, or unrealistically time consuming to solve, through traditional computational strategies. To address the need for speedy dissemination of new ideas in this field to a broad spectrum of neural network users, designers and implementers, Oxford University Press and the Institute of Physics have joined forces to create a major reference publication devoted to neural network fundamentals, models, algorithms, applications and implementations. This work is intended to become the standard reference resource for the neural network community. The Handbook of Neural Computation will be produced in parallel in two updatable formats, looseleaf paper and CD-ROM, and will be kept up to date by means of supplements published on a regular basis. Details of new architectures, algorithms and applications may be submitted to the Handbook editors for peer review and possible inclusion in a future supplement to the Handbook. In this way we will create a moving compendium of the state of the art of neural computation. Key features of the Handbook of Neural Computation: * A hands-on guide to the design and implementation of neural networks * A comprehensive source of reference for all neural network users, designers and implementers * Provides an information pathway between scientists and engineers in different disciplines who apply neural networks to generically similar problems * Provides timely information in a rapidly changing field