No abstract

The Backpropagation technique for supervised learning of internal representations in multi4ayer artificial neural networks is an effective approach for solution of the gradient descent problem. However, as a primarily deterministic solution, it will attempt to take the best path to the nearest minimum, whether global or local. If a local minimum is reached, the network will fail to learn or will learn a poor approximation of the solution. This paper describes a novel approach to the Backpropagation model based on Simulated Annealing. This modified learning model is designed to provide an effective means of escape from local minima. The system is shown to converge more reliably and much faster than traditional noise insertion techniques. Due to the characteristics of the cooling schedule, the system also demonstrates a more consistent training profile.

Connectionist modeling is computationally intensive. Until parallel computers become more widely available, supercomputing resources can be exploited. This paper describes a neural network simulator (NNS) written in FORTRAN for supercomputers. The present simulation engine consists of code for the backpropagation method of changing weights in connectionist models. A file interface reports simulation results in a variety of formats. The file interface also contains an interpreter for an input file through which the network structure is defined, the problem is represented, and various parameters are set. The input-file syntax is described in detail. NNS has been used both as an instructional aid and as a research tool. A simulation of "recovery of unrehearsed associations" is used to illustrate the use of the input file and to demonstrate the performance of NNS. Versions of NNS have been written for the Cray X-MP/48 and for the IBM 3090.In his presidential address to the Society for Computers in Psychology, Walter Schneider explored the profound and far-reaching impact of connectionist models on psychology (Schneider, 1987). The interest in connectionist models, if anything, has intensified; a recent issue of the Journal of Memory and Language was devoted to connectionist models, and the stream of books, journal articles, and papers and symposia at the meetings of the Psychonomic and Cognitive Science societies continues unabated. A collection of reprints covering important developments in the history of connectionism has been assembled by Anderson and Rosenfeld (1988), and critical assessments of the strengths and weaknesses of connectionist approaches to cognition have appeared (Holyoak,

No abstract