Optical random micro-phase-shift DropConnect in a diffractive deep neural network

The formulation and training of unitary neural networks is the basis of an active modulation diffractive deep neural network. In this Letter, an optical random phase DropConnect is implemented on an optical weight to manipulate a jillion of optical connections in the form of massively parallel subnetworks, in which a micro-phase assumed as an essential ingredient is drilled into Bernoulli holes to enable training convergence, and malposed deflections of the geometrical phase ray are reformulated constantly in epochs, allowing for enhancement of statistical inference. Optically, the random micro-phase-shift acts like a random phase sparse griddle with respect to values and positions, and is operated in the optical path of a projective imaging system. We investigate the performance of the full-drilling and part-drilling phenomena. In general, random micro-phase-shift part-drilling outperforms its full-drilling counterpart both in the training and inference since there are more possible recombinations of geometrical ray deflections induced by random phase DropConnect. (C) 2022 Optica Publishing Group

Automated summary

This Letter presents a unitary neural network based on optical random phase DropConnect, which introduces a micro-phase to achieve training convergence and enhance statistical inference. The study reveals that the partial drilling of random micro-phase-shift outperforms the full-drilling counterpart in both training and inference.