All-optical information processing capacity of diffractive networks

Abstract

We analyze the information processing capacity of diffractive optical networks to reveal that increasing the total number of diffractive features, i.e., neurons, within a network linearly increases the dimensionality of the complex-valued linear transformation space of the network, up to a limit dictated by the input and output fields-of-view. We further show that deeper diffractive neural networks formed by larger numbers of diffractive surfaces can cover a higher-dimensional subspace of the complex-valued linear transformations between a larger input field-of-view and a larger output field-of-view, increasing the learning capability and approximation power of the optical network.