DocumentCode :
285180
Title :
High-capacity discrete exponential BAM
Author :
Wang, Chua-Chin ; Don, Hon-Son
Author_Institution :
Dept. of Electr. Eng., State Univ. of New York, Stony Brook, NY, USA
Volume :
2
fYear :
1992
fDate :
7-11 Jun 1992
Firstpage :
178
Abstract :
A bidirectional associative memory (BAM) with high capacity for storage of pattern pairs is proposed. The associative memory takes advantage of the exponential nonlinearity in the evolution equations such that the signal-noise-ratio (SNR) is significantly increased. The increase of SNR consequently enhances the capacity of the BAM. An energy function is defined. The energy of the exponential BAM decreases as the recall process proceeds, ensuring the stability of the system. The monotonic decrease of the energy of the exponential BAM during the recall process ensures it will reach a local minimum
Keywords :
content-addressable storage; energy function; exponential nonlinearity; high speed discrete exponential bidirectional associative memory; pattern pairs storage; recall process; signal-noise-ratio; Associative memory; Autocorrelation; Bismuth; Hamming distance; Magnesium compounds; Nonlinear equations; Reverberation; Stability; Very large scale integration; Voltage;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Neural Networks, 1992. IJCNN., International Joint Conference on
Conference_Location :
Baltimore, MD
Print_ISBN :
0-7803-0559-0
Type :
conf
DOI :
10.1109/IJCNN.1992.227011
Filename :
227011
Link To Document :
بازگشت