Bibliographic Citation
Document | For copies of Journal Articles, please contact the Publisher or your local public or university library and refer to the information in the Resource Relation field. For copies of other documents, please see the Availability, Publisher, Research Organization, Resource Relation and/or Author (affiliation information) fields and/or Document Availability. |
---|---|
Title | Unlearning dynamics in Hopfield neural network |
Creator/Author | Plakhov, A.Yu. [Institute of Physicotechnical Problems, Moscow (Russian Federation)] |
Publication Date | 1995 Mar 01 |
OSTI Identifier | OSTI ID: 223777 |
Other Number(s) | RPQEAC; ISSN 0033-8443 |
Resource Type | Journal Article |
Resource Relation | Radiophysics and Quantum Electronics ; VOL. 37 ; ISSUE: 9 ; PBD: Mar 1995; TN: Translated from Izvestiya Vysshikh Uchebnykh Zavedenii, Radiofizika; 37: No. 9, 1104-1115(Sep 1994) |
Subject | 99 MATHEMATICS, COMPUTERS, INFORMATION SCIENCE, MANAGEMENT, LAW, MISCELLANEOUS ; NEURAL NETWORKS; LEARNING; ALGORITHMS; CONVERGENCE; ITERATIVE METHODS |
Description/Abstract | The dynamics of a convergent iterative unlearning algorithm proposed earlier is examined. A selfconsistent system of equations of the spectral dynamics of a synaptic matrix is obtained at the thermodynamic limit. The unlearning intensity (which varies during the iteration process) that optimizes the algorithm`s rate of convergence on the projector matrix is found. The synaptic-matrix spectrum dynamics for optimal unlearning is determined. |
Country of Publication | United States |
Language | English |
Format | pp. 711-718 ; PL: |
System Entry Date | 2001 May 04 |
Top |