Deep Learning with Coherent Nanophotonic Circuits

TL;DR

This paper introduces a novel fully-optical neural network architecture leveraging nanophotonic circuits, achieving significantly higher speed and energy efficiency than traditional electronic neural networks, demonstrated through experimental validation.

Contribution

The paper proposes a new nanophotonic architecture for neural networks that offers substantial improvements in speed and power efficiency, validated by experimental implementation.

Findings

Achieves at least 100x faster computation than electronic counterparts

Reduces power consumption by approximately 1000x

Demonstrates feasibility with a programmable nanophotonic processor

Abstract

Artificial Neural Networks are computational network models inspired by signal processing in the brain. These models have dramatically improved the performance of many learning tasks, including speech and object recognition. However, today's computing hardware is inefficient at implementing neural networks, in large part because much of it was designed for von Neumann computing schemes. Significant effort has been made to develop electronic architectures tuned to implement artificial neural networks that improve upon both computational speed and energy efficiency. Here, we propose a new architecture for a fully-optical neural network that, using unique advantages of optics, promises a computational speed enhancement of at least two orders of magnitude over the state-of-the-art and three orders of magnitude in power efficiency for conventional learning tasks. We experimentally demonstrate essential parts of our architecture using a programmable nanophotonic processor.