Coherent optical neuron control based on reinforcement learning

Optical neural networks take optical neurons as the corner-stone to achieve complex functions. The coherent optical neuron has become one of the mainstream implementa-tions because it can effectively perform natural and even complex number calculations. However, its state variabil-ity and requirement for reliability and effectiveness render traditional control methods no longer applicable. In this Letter, deep reinforcement coherent optical neuron control (DRCON) is proposed, and its effectiveness is experimen-tally demonstrated. Compared with the standard stochastic gradient descent, the average convergence rate of DRCON is 33% faster, while the effective number of bits increases from less than 2 bits to 5.5 bits. DRCON is a promising first step for large-scale optical neural network control. (c) 2023 Optica Publishing Group

Automated summary

Optical neural networks utilize optical neurons to achieve complex functions. The proposed deep reinforcement coherent optical neuron control (DRCON) method improves convergence rate and effective number of bits, showing promise for large-scale optical neural network control.