Title :
Generalised intraconnected bidirectional associative memories
Author_Institution :
Dept. of Electron. Eng., Ta-Hwa Inst. of Technol., Hsin Chu, Taiwan
fDate :
4/16/1998 12:00:00 AM
Abstract :
A general model of the intraconnected bidirectional associative memory (GIBAM) is proposed. In a GIBAM, states are represented by complex values on the unit circle of the complex plane, and the weight matrices are learned using the generalised inverse technique. The stability of the GIBAM is demonstrated by defining an energy function which decreases with a change in neuron states. Computer simulation demonstrates that the GIBAM has a much higher storage capacity and much better error correcting capability than Jengs modified IBAM
Keywords :
content-addressable storage; recurrent neural nets; GIBAM; complex plane; computer simulation; energy function; error correction; generalised intraconnected bidirectional associative memory; generalised inverse technique; learning; neuron states; stability; storage capacity; weight matrix;
Journal_Title :
Electronics Letters
DOI :
10.1049/el:19980596