DocumentCode :
1869162
Title :
A case study for the implementation of a stochastic bit stream neuron; the choice between electrical and optical interconnects
Author :
Hands, M.A. ; Peiffer, W. ; Thienpont, H. ; Kirk, A. ; Hall, T.J.
Author_Institution :
Dept. of Appl. Phys., Vrije Univ., Brussels, Belgium
fYear :
1995
fDate :
23-24 Oct 1995
Firstpage :
63
Lastpage :
75
Abstract :
A neural network architecture is described which uses stochastic processing techniques to perform the weighted input multiplication, summation and thresholding processes of a neuron using the optimal amount of hardware. It is argued that the advantage of this approach is that it will allow large neural networks to be fabricated with relatively small amounts of hardware. The architecture allows a choice to be made between the speed and accuracy of processing, as well as a choice of hardware. Implementations of a bit stream neuron using electronic, optoelectronic and optical hardware are developed and their capabilities are compared based on speed of processing and network size. The aim of the study is to investigate the capabilities of optical logic in distributed processing systems, together with the use of the optical thyristor as logic elements. It is shown that optical processing and optical interconnection allows a simplification of the processing sequence and allows the parallelism of distributed systems to be utilised
Keywords :
distributed processing; neural chips; neural net architecture; optical interconnections; optical logic; optical neural nets; photothyristors; stochastic processes; bit stream neuron; case study; distributed processing systems; large neural networks; logic elements; neural network architecture; optical hardware; optical interconnection; optical interconnects; optical logic; optical processing; optical thyristor; parallelism; stochastic bit stream neuron; stochastic processing techniques; thresholding processes; weighted input multiplication; Distributed processing; Logic; Neural network hardware; Neural networks; Neurons; Optical computing; Optical fiber networks; Optical interconnections; Stochastic processes; Thyristors;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Massively Parallel Processing Using Optical Interconnections, 1995., Proceedings of the Second International Conference on
Conference_Location :
San Antonio, TX
Print_ISBN :
0-8186-7101-7
Type :
conf
DOI :
10.1109/MPPOI.1995.528629
Filename :
528629
Link To Document :
بازگشت