PROGRAMMABLE IMPULSE NEURAL CIRCUITS

被引:33
作者
MEADOR, JL
WU, A
COLE, C
NINTUNZE, N
CHINTRAKULCHAI, P
机构
[1] Department of Electrical Engineering and Computer Science, Washington State University, Pullman
来源
IEEE TRANSACTIONS ON NEURAL NETWORKS | 1991年 / 2卷 / 01期
关键词
D O I
10.1109/72.80295
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Impulse neural networks use pulse sequences to communicate instantaneous neuron activation levels. This paper describes CMOS electronic circuits, which emulate natural neurons at a more detailed level than that typically employed by artificial neural network models. A pulse-firing circuit which realizes general short-term neuron dynamics is discussed. Both fixed and programmable synapse circuits for realizing long-term dynamics are also described. Together, these establish the basic structures required for the implementation of programmable impulse neural networks.
引用
收藏
页码:101 / 109
页数:9
相关论文
共 41 条
[1]  
ALLEN P, 1987, CMOS ANALOG CIRCUIT, P497
[2]  
[Anonymous], 1987, LEARNING INTERNAL RE
[3]  
[Anonymous], 1989, ANALOG VLSI NEURAL S
[4]  
Berry M., 1980, Current Topics in Developmental Biology, V15, P67
[5]   A HETEROASSOCIATIVE MEMORY USING CURRENT-MODE MOS ANALOG VLSI CIRCUITS [J].
BOAHEN, KA ;
POULIQUEN, PO ;
ANDREOU, AG ;
JENKINS, RE .
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS, 1989, 36 (05) :747-755
[6]  
BORSTROM T, 1989, P IEEE ISCAS, P1227
[7]  
Caianiello E.R., 1961, J THEOR BIOL, V2, P204
[8]   SILICON MODELS OF ASSOCIATIVE LEARNING IN APLYSIA [J].
CARD, HC ;
MOORE, WR .
NEURAL NETWORKS, 1990, 3 (03) :333-346
[9]  
CARPENTER GA, 1986, HYBRID OPTICAL COMPU
[10]  
CARPENTER GA, 1988, NEURAL NETWORKS NATU, P251