These volumes explore recent research in neural networks that has advanced our understanding of human and machine perception. Contributions from international researchers address both theoretical and practical issues related to the feasibility of neural network models to explain human perception and implement machine perception. Volume 1 covers models for understanding human perception in terms of distributed computation as well as examples of neural network models for machine perception and volume 2 examines computational and adaptational problems related to the use of neural systems and discusses the corresponding hardware architectures needed to implement neural networks for perception.

Table of Contents:
Part 1 Human and machine perception: visual cortex - window on the biological basis of learning and memory, L. Cooper; a network model of object recognition in human vision, S. Edelman; a cortically based model for integration in visual perception, F. Finkel, et al; the symmetric organization of parallel cortical systems for form and motion perception, S. Grossbert; the structure and interpretation of neuronal codes in the visual system, B. Richmond and L.M. Optican; self-organization of functional architecture in the cerebral cortex, S. Tanaka; filters versus textons in human and machine texture discrimination, D. Williams and B. julesz; two-dimensional maps and biological vision - representing three-dimensional space, G.L. Zimmerman. Part 2 Machine perception: wisards and other weightless neurons, I. Aleksander; multi-dimensional linera lattice for Fourier and Gabor transforms, multiple-scale Gaussian filtering and edge detection, J. Ben-Arie; aspects of invariant patterns and object recognition, T. Caelli, et al; a neural network architecture for fast on-line supervised learning and pattern recognition, G. Carpenter, et al; neural network approaches to color vision, A. Hurlbert; adaptive sensory-motor co-ordination through self-consistency, M. Kuperstein; finding boundaries in images, J. Malik and P. Perona; compression of remotely sensed images using self-organizing feature maps, M. Manohar and J. Tilton; region growing using neural networks, T. Reed; vision and space-variant sensing, G. Sandini and M. Tistarelli; learning and recognizing three-dimensional objects for multiple views in a neural system, M. Seibert and A. Waxman; hybrid symbolic-neural methods for improved recognition using high-level visual features, G. Towell and J. Shavlik; multiscale and distributed visual representations and mappings for invariant low-level perception, H. Wechsler; symmetry - a context-free cue for foveated vision, Y. Yeshurun, et al; a neural network for motion processing, Y.T. Zhou and R. Chellappa.