Noise analysis of polarization-based optoelectronic connectionist machines

Adaptive optical systems such as the bipolar, polarization-based optical connectionist machine are capable of operating in the presence of substantial noise generated by optoelectronic devices such as spatial light modulators, sources, and detectors. Results are presented on two optoelectronic connectionist machines that implement the single-layer delta rule and backward error propagation neural network algorithms and analyze the influence of noise on their performance. Results show that an optoelectronic neural network with 200 input units can easily classify 30 random patterns with a spatial light modulator contrast ratio of 10:1 and output cross talk of 10 percent.