Accession Number : ADA185394
Title : Connectionist Learning Procedures.
Descriptive Note : Technical rept.,
Corporate Author : CARNEGIE-MELLON UNIV PITTSBURGH PA DEPT OF COMPUTER SCIENCE
Personal Author(s) : Hinton, Geoffrey E
PDF Url : ADA185394
Report Date : 04 Sep 1987
Pagination or Media Count : 66
Abstract : A major goal of research on networks of neuron-like processing units is to discover efficient learning procedures that allow these networks to construct complex internal representations of their environment. The learning procedures must be capable of modifying the connection strengths in such a way that internal units which are not part of the input or output come to represent important features of the task domain. Several interesting gradient-descent procedures have recently been discovered. Each connection computes the derivative, with respect to the connection strength, of a global measure of the error in the the performance of the network. The strength is then adjusted in the direction that decrease the error. These relatively simple, gradient-descent learning procedures work well for small tasks and the new challenge is to find ways of improving the speed of learning so that they can be applied to larger, more realistic tasks.
Descriptors : *NEURAL NETS, *STATISTICAL ANALYSIS, LEARNING, MATHEMATICAL MODELS, COMPUTATIONS, SYSTEMS ENGINEERING
Subject Categories : Cybernetics
Statistics and Probability
Distribution Statement : APPROVED FOR PUBLIC RELEASE