C. D. Jr. Gelatt’s research while affiliated with IBM Research - Thomas J. Watson Research Center and other places

Researchers will find Neurocomputing an essential guide to the concepts employed in this field that have been taken from disciplines as varied as neuroscience, psychology, cognitive science, engineering, and physics. A number of these important historical papers contain ideas that have not yet been fully exploited, while the more recent articles define the current direction of neurocomputing and point to future research. Each article has an introduction that places it in historical and intellectual perspective. Included among the 43 articles are the pioneering contributions of McCulloch and Pitts, Hebb, and Lashley; innovative work by Von Neumann, Minsky and Papert, Cooper, Grossberg, and Kohonen; exciting new developments in parallel distributed processing. Bradford Books imprint

There is a deep and useful connection between statistical mechanics (the behavior of systems with many degrees of freedom in thermal equilibrium at a finite temperature) and multivariate or combinatorial optimization (finding the minimum of a given function depending on many parameters). A detailed analogy with annealing in solids provides a framework for optimization of the properties of very large and complex systems. This connection to statistical mechanics exposes new information and provides an unfamiliar perspective on traditional optimization problems and methods.

The following questions are considered: How do itinerant d electrons of the Heusler alloys produce magnetic moments that are completely localized on the Mn atoms? What is the microscopic origin of Invar anomalies? Why is elemental antiferromagnetism confined to Cr, Mn, and Fe? Why do the Fe atoms in Fe 3 Si carry two distinctly different magnetic moments? Can we use our understanding of transiton‐metal magnetism to ’’design’’ new magnetic compounds composed of nonmagnetic elements? Our answers to these questions are based on the local‐spin‐density theory of electronic exchange and correlation, implemented using parameter‐free self‐consistent energy‐band calculations.