A complete, parallel and autonomous photonic neural network in a semiconductor multimode laser

TL;DR

This paper demonstrates a fully parallel, hardware-implemented photonic neural network using a semiconductor laser with over 130 nodes, capable of performing various digital tasks with high accuracy and scalability beyond traditional electronic systems.

Contribution

It introduces the first fully parallel and integrated photonic neural network utilizing a semiconductor laser and multimode fiber, enabling high-speed, scalable neural processing in hardware.

Findings

Achieved < 0.9×10^-3 error rate in digit recognition.

Demonstrated 2-bit XOR with 2.9×10^-2 error rate.

System scalable to larger sizes and >20 GHz bandwidth.

Abstract

Neural networks are one of the disruptive computing concepts of our time. However, they fundamentally differ from classical, algorithmic computing in a number of fundamental aspects. These differences result in equally fundamental, severe and relevant challenges for neural network computing using current computing substrates. Neural networks urge for parallelism across the entire processor and for a co-location of memory and arithmetic, i.e. beyond von Neumann architectures. Parallelism in particular made photonics a highly promising platform, yet until now scalable and integratable concepts are scarce. Here, we demonstrate for the first time how a fully parallel and fully implemented photonic neural network can be realized using spatially distributed modes of an efficient and fast semiconductor laser. Importantly, all neural network connections are realized in hardware, and our processor produces results without pre- or post-processing. 130+ nodes are implemented in a large-area vertical cavity surface emitting laser, input and output weights are realized via the complex transmission matrix of a multimode fiber and a digital micro-mirror array, respectively. We train the readout weights to perform 2-bit header recognition, a 2-bit XOR and 2-bit digital analog conversion, and obtain < 0.9 10^-3 and 2.9 10^-2 error rates for digit recognition and XOR, respectively. Finally, the digital analog conversion can be realized with a standard deviation of only 5.4 10^-2. Our system is scalable to much larger sizes and to bandwidths in excess of 20 GHz.