DocumentCode :
1649638
Title :
Pulse-stream arithmetic in programmable neural networks
Author :
Murray, A.F. ; Hamilton, A. ; Reekie, H.M. ; Tarassenko, L.
Author_Institution :
Dept. of Electr. Eng., Edinburgh Univ., UK
fYear :
1989
Firstpage :
1210
Abstract :
A pulse-stream signaling mechanism is described that is analogous to that found in natural neural systems. Previous work has resulted in the development of synthetic neural networks implemented as VLSI devices using pulse streams to represent neural states and a time-chopping technique to implement multiplication by synaptic weights. Synaptic weights are stored on-chip in digital memory. An alternative method for representing synaptic weights is described which uses dynamic storage capacitors to hold the charge proportional to synaptic weight. The capacitive storage devices are refreshed from off-chip digital RAM via a digital-to-analog converter. The presence, absence, and rate of pulse firing of the neuron are used to represent its state. Multiplication of a neuron state by a synaptic weight is performed by modifying the width of individual pulses passing through the synapse. A circuit that performs this function is described. The small synaptic circuit that results allows relatively high levels of integration in comparison to other programmable silicon neural forms
Keywords :
VLSI; digital arithmetic; neural nets; VLSI; capacitive storage devices; digital-to-analog converter; dynamic storage capacitors; neural states; off-chip digital RAM; programmable neural networks; pulse firing; pulse-stream signaling mechanism; synaptic weights; time-chopping technique; Arithmetic; Capacitors; Circuits; Digital-analog conversion; Neural networks; Neurons; Random access memory; Read-write memory; Space vector pulse width modulation; Very large scale integration;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Circuits and Systems, 1989., IEEE International Symposium on
Conference_Location :
Portland, OR
Type :
conf
DOI :
10.1109/ISCAS.1989.100571
Filename :
100571
Link To Document :
بازگشت