Performance of back propagation networks for associative database retrieval

Vladimir Cherkassky, Nikolaos Vassilas

Research output: Contribution to conferencePaperpeer-review

11 Scopus citations

Abstract

Backpropagation networks have been successfully used to perform a variety of input-output mapping tasks for recognition, generalization, and classification. In spite of this method's popularity, virtually nothing is known about its saturation/capacity and, in more general terms, about its performance as an associative memory. The authors address these issues using associative database retrieval as an original application domain. Experimental results show that the quality of recall and the network capacity are very significantly affected by the network topology (the number of hidden units), data representation (encoding), and the choice of learning parameters. On the basis of their results and the fact that backpropagation learning is not recursive, the authors conclude that backpropagation networks can be used mainly as read-only associative memories and represent a poor choice for read-and-write associative memories.

Original languageEnglish (US)
Pages77-84
Number of pages8
DOIs
StatePublished - Jan 1 1989
EventIJCNN International Joint Conference on Neural Networks - Washington, DC, USA
Duration: Jun 18 1989Jun 22 1989

Other

OtherIJCNN International Joint Conference on Neural Networks
CityWashington, DC, USA
Period6/18/896/22/89

Fingerprint Dive into the research topics of 'Performance of back propagation networks for associative database retrieval'. Together they form a unique fingerprint.

Cite this