Nonlinear Inference Capacity of Fiber-Optical Extreme Learning Machines

TL;DR

This paper explores the nonlinear inference capacity of fiber-optical Extreme Learning Machines, demonstrating their potential to outperform deep neural networks in classification tasks by leveraging optical nonlinearity.

Contribution

It introduces the concept of nonlinear inference capacity in optical neuromorphic computing and shows how fiber-based systems can surpass deep neural networks in classification performance.

Findings

Nonlinear optical fiber systems can exceed deep neural network performance.

Classification performance correlates with fiber nonlinear dynamics.

The framework enables benchmarking physics-inspired computing architectures.

Abstract

The intrinsic complexity of nonlinear optical phenomena offers a fundamentally new resource to analog brain-inspired computing, with the potential to address the pressing energy requirements of artificial intelligence. We introduce and investigate the concept of nonlinear inference capacity in optical neuromorphic computing in highly nonlinear fiber-based optical Extreme Learning Machines. We demonstrate that this capacity scales with nonlinearity to the point where it surpasses the performance of a deep neural network model with five hidden layers on a scalable nonlinear classification benchmark. By comparing normal and anomalous dispersion fibers under various operating conditions and against digital classifiers, we observe a direct correlation between the system's nonlinear dynamics and its classification performance. Our findings suggest that image recognition tasks, such as MNIST, are incomplete in showcasing deep computing capabilities in analog hardware. Our approach provides a framework for evaluating and comparing computational capabilities, particularly their ability to emulate deep networks, across different physical and digital platforms, paving the way for a more generalized set of benchmarks for unconventional, physics-inspired computing architectures.