Title :
Capacity of various exponential bidirectional associative memories
Author :
Eom, Tae-Dok ; Lee, Choon-Young ; Lee, Ju-Jang
Author_Institution :
Dept. of Electr. Eng., Korea Adv. Inst. of Sci. & Technol., Taejon, South Korea
fDate :
3/30/2000 12:00:00 AM
Abstract :
Bidirectional associative memory (BAM) has been widely used to solve classification problems such as pattern recognition, data compression, etc. Since Jeng et al. (1990) proposed the exponential BAM (eBAM), which has a high storage capacity and error-correction capability as well as being simple to implement, a great deal of research has gone into further improving its performance. The capacities of various eBAMs are derived and compared
Keywords :
content-addressable storage; pattern classification; probability; classification problems; data compression; error-correction capability; exponential BAM; exponential bidirectional associative memories; pattern recognition; storage capacity;
Journal_Title :
Electronics Letters
DOI :
10.1049/el:20000540