论文信息 - Influence of interconnection weight discretization and noise in an optoelectronic neural network.

Influence of interconnection weight discretization and noise in an optoelectronic neural network.

The effect of discretizing interconnection weight strengths in an optoelectronic learning neural network based on the backpropagation algorithm is investigated. We discuss how discretization arises in such an implementation. Using computer simulations we find that learning performance, as tested on the two-input XOR problem, is poor but that the addition of noise to the system results in substantial improvement.

E. Paek | P. F. Liao | A. Marrakchi | J. S. Patel | A. V. Von Lehmen

[1] J W Goodman,et al. Fully parallel, high-speed incoherent optical method for performing discrete Fourier transforms. , 1978, Optics letters.

[2] N. Clark,et al. Submicrosecond bistable electro‐optic switching in liquid crystals , 1980 .

[3] J J Hopfield,et al. Neural networks and physical systems with emergent collective computational abilities. , 1982, Proceedings of the National Academy of Sciences of the United States of America.

[4] Demetri Psaltis,et al. Two-Dimensional Magneto-Optic Spatial Light Modulator For Signal Processing , 1983 .

[5] N H Farhat. Architectures for optoelectronic analogs of self-organizing neural networks. , 1987, Optics letters.

[6] Sadik C. Esener,et al. One-Dimensional Silicon/PLZT Spatial Light Modulators , 1987 .

[7] N H Farhat,et al. Optoelectronic analogs of self-programming neural nets: architecture and methodologies for implementing fast stochastic learning by simulated annealing. , 1987, Applied optics.