Title :
Towards a fully parallel stochastic Hopfield neural network
Author :
Torralba, A. ; Colodro, F.
Author_Institution :
Dpto. de Ingenieria Electron., Seville Univ., Spain
Abstract :
The authors present two digital circuits to implement a fully parallel stochastic Hopfield neural network (SHNN). In a parallel SHNN all the n × n stochastic signals sij that pulse with probability proportional to the synapse inputs are simultaneously available. The proposed circuits calculate the function Fi that accumulates the number of positive (negative) stochastic input pulses to neuron i
Keywords :
Hopfield neural nets; neural chips; digital circuits; fully parallel neural net; stochastic Hopfield neural network; stochastic input pulses; stochastic signals; synapse inputs; Adders; CMOS technology; Convergence; Counting circuits; Hopfield neural networks; Logic circuits; Neurons; Propagation delay; Registers; Stochastic processes;
Conference_Titel :
Circuits and Systems, 1993., ISCAS '93, 1993 IEEE International Symposium on
Conference_Location :
Chicago, IL
Print_ISBN :
0-7803-1281-3
DOI :
10.1109/ISCAS.1993.394334
