Photonic extreme learning machine by free-space optical propagation

TL;DR

This paper introduces a simple, scalable, and energy-efficient photonic neural network using free-space optical propagation and spatial light modulation, demonstrating competitive learning performance for classification and regression tasks.

Contribution

It presents a novel neuromorphic photonic scheme based on free-space propagation, avoiding complex optical elements and enabling easy training and scalability.

Findings

Achieved classification and regression accuracies comparable to digital ELMs.

Demonstrated a simple, scalable, and energy-efficient optical learning device.

Enabled real-time neuromorphic processing of optical data.

Abstract

Photonic brain-inspired platforms are emerging as novel analog computing devices, enabling fast and energy-efficient operations for machine learning. These artificial neural networks generally require tailored optical elements, such as integrated photonic circuits, engineered diffractive layers, nanophotonic materials, or time-delay schemes, which are challenging to train or stabilize. Here we present a neuromorphic photonic scheme - photonic extreme learning machines - that can be implemented simply by using an optical encoder and coherent wave propagation in free space. We realize the concept through spatial light modulation of a laser beam, with the far field that acts as feature mapping space. We experimentally demonstrated learning from data on various classification and regression tasks, achieving accuracies comparable to digital extreme learning machines. Our findings point out an optical machine learning device that is easy-to-train, energetically efficient, scalable and fabrication-constraint free. The scheme can be generalized to a plethora of photonic systems, opening the route to real-time neuromorphic processing of optical data.