Information processing capacity of diffractive surfaces

Abstract

We analyze the information processing capacity of coherent optical networks formed by trainable diffractive surfaces to prove that the dimensionality of the solution space describing the set of all-optical transformations established by a diffractive network increases linearly with the number of diffractive surfaces, up to a limit determined by the size of the input/output fields-of-view. Deeper diffractive networks formed by larger numbers of trainable diffractive surfaces span a broader subspace of the complex-valued transformations between larger input/output fields-of-view, and present major advantages in terms of their function approximation power, inference accuracy and learning/generalization capabilities compared to a single diffractive surface.