Storage capacity and retrieval properties of an auto-associative general neural unit
- 1 January 1991
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. ii, 959 vol.2
- https://doi.org/10.1109/ijcnn.1991.155601
Abstract
Summary form only given, as follows. The probability of disruption of patterns stored in a general neural unit, used as an auto-associator, was derived. It was shown that the network can store about the same number of patterns as the number of inputs per node, with an acceptable error rate. The retrieval equations of the network were established in the case of three arbitrary stored patterns.<>Keywords
This publication has 0 references indexed in Scilit: