Title :
An analysis of practical capacity of exponential bidirectional associative memory
Author :
Wang, Chua-Chin ; Tsai, Chang-Rong
Author_Institution :
Dept. of Electr. Eng., Nat. Sun Yat-Sen Univ., Kaohsiung, Taiwan
fDate :
27 Jun-2 Jul 1994
Abstract :
The practical capacity of exponential bidirectional associative memory (eBAM) considering fault tolerance and fixed dynamic range of VLSI circuits is discussed. Several factors are taken into consideration in the implementation of an eBAM VLSI circuits. First, the fault tolerance requirement leads to the discovery of the attraction radius of the basin for each stored pattern pair. Second, the bit-error probability of the eBAM has to be optimally small when a huge amount of pattern pairs are encoded in the eBAM. Third, the fixed dynamic range of a transistor or a diode operating in the subthreshold region results in a limited length of each stored pattern. Hence, the signal-noise-ratio (SNR) analysis approach is adopted to find the attraction radius, and the practical capacity. A maximal bit-error probability (Pe) is estimated. A maximal length of patterns under a fixed dynamic range is derived
Keywords :
VLSI; content-addressable storage; fault tolerant computing; memory architecture; neural chips; neural nets; probability; VLSI circuits; attraction radius; bit-error probability; diode; eBAM; eBAM VLSI circuits; exponential bidirectional associative memory; fault tolerance; fault tolerance requirement; fixed dynamic range; maximal bit-error probability; pattern pairs; signal-noise-ratio analysis; stored pattern pair; subthreshold region; transistor; Associative memory; Circuits; Diodes; Dynamic range; Equations; Fault tolerance; Magnesium compounds; Neural networks; Signal analysis; Very large scale integration;
Conference_Titel :
Neural Networks, 1994. IEEE World Congress on Computational Intelligence., 1994 IEEE International Conference on
Conference_Location :
Orlando, FL
Print_ISBN :
0-7803-1901-X
DOI :
10.1109/ICNN.1994.374332