National Technical Reports Library

The National Technical Information Service acquires, indexes, abstracts, and archives the largest collection of U.S. government-sponsored technical reports in existence. The NTRL offers online, free and open access to these authenticated government technical reports. Technical reports and documents in its repository may be available online for free either from the issuing federal agency, the U.S. Government Publishing Office’s Federal Digital System website, or through search engines.

Details

Learning Internal Representations by Error Propagation.

ADA164453

Publication Date	1985
Personal Author	Rumelhart, D. E.; Hinton, G. E.; Williams, R. J.
Page Count	49
Abstract	This paper presents a generalization of the perception learning procedure for learning the correct sets of connections for arbitrary networks. The rule, falled the generalized delta rule, is a simple scheme for implementing a gradient descent method for finding weights that minimize the sum squared error of the system's performance. The major theoretical contribution of the work is the procedure called error propagation, whereby the gradient can be determined by individual units of the network based only on locally available information. The major empirical contribution of the work is to show that the problem of local minima not serious in this application of gradient descent. Keywords: Learning; networks; Perceptrons; Adaptive systems; Learning machines; and Back propagation.
Keywords	Adaptive systems Learning Networks Descent Errors Gradients Internal Learning machines Propagation Weight Perception
Source Agency	Non Paid ADAS
NTIS Subject Category	92D - Education, Law, & Humanities
Corporate Authors	California Univ., San Diego, La Jolla. Inst. for Cognitive Science.
Document Type	Technical Report
Title Note	Technical rept. Mar-Sep 85.
NTIS Issue Number	198611
Contract Number	N00014-85-K-04507

Learning Internal Representations by Error Propagation.

Learning Internal Representations by Error Propagation.
ADA164453

Publication Date	1985
Personal Author	Rumelhart, D. E.; Hinton, G. E.; Williams, R. J.
Page Count	49
Abstract	This paper presents a generalization of the perception learning procedure for learning the correct sets of connections for arbitrary networks. The rule, falled the generalized delta rule, is a simple scheme for implementing a gradient descent method for finding weights that minimize the sum squared error of the system's performance. The major theoretical contribution of the work is the procedure called error propagation, whereby the gradient can be determined by individual units of the network based only on locally available information. The major empirical contribution of the work is to show that the problem of local minima not serious in this application of gradient descent. Keywords: Learning; networks; Perceptrons; Adaptive systems; Learning machines; and Back propagation.
Keywords	Adaptive systems Learning Networks Descent Errors Gradients Internal Learning machines Propagation Weight Perception
Source Agency	Non Paid ADAS
NTIS Subject Category	92D - Education, Law, & Humanities
Corporate Authors	California Univ., San Diego, La Jolla. Inst. for Cognitive Science.
Document Type	Technical Report
Title Note	Technical rept. Mar-Sep 85.
NTIS Issue Number	198611
Contract Number	N00014-85-K-04507