A Coherent Perceptron for All-Optical Learning

TL;DR

This paper introduces an all-optical perceptron model using nonlinear photonic circuits that can learn classification boundaries iteratively, demonstrating near-theoretical error bounds through simulations.

Contribution

It presents a novel coherent perceptron architecture for all-optical learning, enabling programmable linear transformations and iterative training in photonic circuits.

Findings

Device nearly attains theoretical error bound

Demonstrates effective all-optical learning

Uses extensive semi-classical stochastic simulations

Abstract

We present nonlinear photonic circuit models for constructing programmable linear transformations and use these to realize a coherent Perceptron, i.e., an all-optical linear classifier capable of learning the classification boundary iteratively from training data through a coherent feedback rule. Through extensive semi-classical stochastic simulations we demonstrate that the device nearly attains the theoretical error bound for a model classification problem.