Optimizing Coherent Integrated Photonic Neural Networks under Random Uncertainties

TL;DR

This paper introduces an optimization approach for silicon-photonic neural networks that enhances power efficiency and robustness against uncertainties, achieving significant reductions in power consumption and accuracy loss.

Contribution

The paper presents a novel optimization method specifically designed to improve power efficiency and robustness in coherent integrated photonic neural networks.

Findings

Reduced network power consumption by 15.3%.

Decreased accuracy loss under uncertainties by 16.1%.

Enhanced robustness of photonic neural networks.

Abstract

We propose an optimization method to improve power efficiency and robustness in silicon-photonic-based coherent integrated photonic neural networks. Our method reduces the network power consumption by 15.3% and the accuracy loss under uncertainties by 16.1%.