Title :
Bimodal stochastic optical learning machine
Author :
Farhat, N.H. ; Shae, Z.-Y.
Author_Institution :
Dept. of Electr. Eng., Pennsylvania Univ., Philadelphia, PA, USA
Abstract :
The authors present the results of numerical and experimental study aimed at optoelectronic realization of networks that can be switched between two distinct operating modes, depending on noise level in the network. The results include fast simulated annealing by noisy thresholding, which demonstrates that the global energy minimum of a small analog test network can be reached in a matter of a few tens of neuron time constants, and stochastic learning with binary weights, which paves the way for the use of fast binary and nonvolatile spatial light modulators to realize synaptic modifications.<>
Keywords :
learning systems; neural nets; noise; optical information processing; stochastic processes; bimodal stochastic optimal learning machine; binary weights; fast simulated annealing; global energy minimum; noise level; noisy thresholding; nonvolatile spatial light modulators; optoelectronic realization; stochastic learning; synaptic modifications; Learning systems; Neural networks; Noise; Optical data processing; Stochastic processes;
Conference_Titel :
Neural Networks, 1988., IEEE International Conference on
Conference_Location :
San Diego, CA, USA
DOI :
10.1109/ICNN.1988.23949
