Practical optoelectronic neural network realizations based on the fault tolerance of the backpropagation algorithm
- 1 March 1996
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks
- Vol. 7 (2) , 488-500
- https://doi.org/10.1109/72.485682
Abstract
This paper describes how the fault tolerance of the backpropagation algorithm can be used to accommodate the realistic (nonideal) transfer characteristics of the optical communication links used, between neural layers, in optoelectronic neural networks. In particular the authors demonstrate that networks, utilizing MSM (metal-semiconductor-metal) photodiodes (PDs) and either LED (light emitting diode) or MQW (multiple quantum well) laser transmitters within these intraneural links, are capable of performing satisfactorily even in the presence of such nonideal device phenomena as: 60% optical crosstalk, 50% optoelectronic device variation, or a thresholded (I(th)=0.5*I(max)) laser output characteristic. Subsequent to this, the authors then show how it is possible to use this fault tolerance to simplify the neuron architecture, to the extent that it consists only of MSM PDs a current amplifier, and an MQW laser. The overall neuron transfer function is then a first-order approximation to the original sigmoidal function.Keywords
This publication has 18 references indexed in Scilit:
- Investigation into effects of device variation on performance of optoelectronic neural networksElectronics Letters, 1993
- 8×18 top emitting independently addressable surface emitting laser arrays with uniform threshold current and low threshold voltageApplied Physics Letters, 1993
- GaAs optoelectronic neuron arraysApplied Optics, 1993
- High-power vertical-cavity surface-emitting lasersElectronics Letters, 1993
- A scalable optoelectronic neural system using free-space optical interconnectsIEEE Transactions on Neural Networks, 1992
- Temperature dependence of GaAs-AlGaAs vertical cavity surface emitting lasersApplied Physics Letters, 1992
- Frequency division multiplexing in analogue neural networkElectronics Letters, 1991
- Variable-sensitivity photodetector that uses a metal–semiconductor–metal structure for optical neural networksOptics Letters, 1991
- Photodetector sensitivity control for weight setting in optoelectronic neural networksApplied Optics, 1991
- 10 Gb/s monolithic integrated MSM-photodiode AlGaAs/GaAs-HEMT optoelectronic receiverIEEE Transactions on Electron Devices, 1991