Measurement-based acceleration of optical computations

TL;DR

This paper explores using collective oscillations in coupled optical resonators to perform matrix-vector multiplication, potentially accelerating neural network computations through optical analog processing.

Contribution

It demonstrates that collective oscillations in coupled resonators can implement matrix-vector multiplication, offering a novel optical approach to accelerate neural network computations.

Findings

Collective oscillations' frequency increases with the number of modes.

Detection time decreases as input vector dimension grows.

System limitations are imposed by optical frequency band restrictions.

Abstract

Analog coprocessors are intensively developing nowadays with the aim to optimize energy computations of neural networks. In this work we focus on the possibility of using detection of collective oscillations in optical systems for computational purposes. We show that in a system of coupled resonators, collective oscillations can be used to implement matrix-vector multiplication. The matrix is formed by the coupling constants between the resonators, and the input vector is formed by the initial occupancies of the involved modes. The frequency of the collective oscillations is growing with the number of the involved modes, similarly to Rabi oscillations. The time needed for their detection, i.e., averaging, decreases with an increase in the input vector dimension. We discuss the limitations imposed on parallel computation in the system by restriction of the allowed optical frequency band.