Title :
Improved exponential bidirectional associative memory
Author :
Chen, Songcan ; Gao, Hang ; Yan, WeI
Author_Institution :
Dept. of Comput. Sci., Nanjing Univ. of Aeronaut. & Astronaut., China
fDate :
1/30/1997 12:00:00 AM
Abstract :
Based on Jeng´s exponential bidirectional associative memory (eBAM) another improved updating rule for eBAMs is presented. In the recalling process of the improved eBAM (IeBAM), the continuity assumption of the eBAM is avoided, and the stability of the system in synchronous and asynchronous modes are proven by defining an energy function which decreases on the change of neuron states. The proposed model greatly improves the performances of the eBAM. Computer simulations demonstrate that the IeBAM has a much higher storage capacity and a better error correcting capability than those of the eBAM
Keywords :
content-addressable storage; error correction; exponential distribution; neural nets; IeBAM; asynchronous modes; continuity assumption; eBAMs; energy function; error correcting capability; exponential bidirectional associative memory; neuron states; recalling process; storage capacity; synchronous modes; updating rule;
Journal_Title :
Electronics Letters
DOI :
10.1049/el:19970155