Title :
Encoding resolution in Hopfield associative memory networks
Author :
Voitovetsky, I. ; Guterman, H.
Author_Institution :
Dept. of Electr. & Comput. Eng., Ben-Gurion Univ. of the Negev, Beer-Sheva, Israel
Abstract :
The number of precision bits for data storage are limited in the hardware implementation of Hopfield type networks. This paper addresses the problem of selection of encoding resolution on the synaptic weights. We investigate the effect of quantization in binary and analog Hopfield networks as a function of data noise and the number of storage patterns. The performance of the networks in terms of recall efficiency was estimated by simulations.
Keywords :
Hopfield neural nets; analogue processing circuits; content-addressable storage; quantisation (signal); Hopfield associative memory networks; data noise; encoding resolution; hardware implementation; precision bits; quantization; recall efficiency; storage patterns; synaptic weights; Associative memory; Conductivity; Encoding; Hardware; Integrated circuit interconnections; Intelligent networks; Neural networks; Neurons; Parallel processing; Quantization;
Conference_Titel :
Electrical and Electronics Engineers in Israel, 1995., Eighteenth Convention of
Conference_Location :
Tel Aviv, Israel
Print_ISBN :
0-7803-2498-6
DOI :
10.1109/EEIS.1995.514160
