Emergent learning: neuromorphic photonic computing with accelerated training

TL;DR

This paper introduces a neuromorphic photonic computing system that uses emergent learning in disordered optical media to store, recognize, and classify patterns with high capacity and reduced digital processing.

Contribution

It demonstrates how emergent learning can be applied to optical media to create a flexible, high-capacity, analog-based neuromorphic computing platform with no need for digital training layers.

Findings

Optical-synaptic matrix described by a dyadic matrix similar to Hebbian matrices.

System can store an almost infinite number of tailored memories (~10^60557).

Enables pattern recognition through intensity comparison without digital transformation.

Abstract

Emergent learning transforms a disordered optical medium into a photonic device capable of storage, recognition, and classification of arbitrary memory patterns. First, we show that the intensity at the output of a multiply scattering system can be described by a dyadic matrix, the optical-synaptic matrix, exhibiting the same form as a Hebbian synaptic matrix containing a single memory. Then, we employ emergent learning - an approach inspired by neuroscience - to exploit the vast dictionary of raw memories inherently available within a disordered optical structure, thereby engineering the optical-synaptic matrix to store a user-defined attractor, or tailored memory. Importantly these photonic structures also works as an optical comparators providing an intensity-based measure of the degree of similitude between a query pattern and the stored pattern, realizing an hardware co-localization between memory and optical operator. Our system has an almost infinite hardware capacity of tailored memories/ operators ($\mathcal{M} \sim 10^{60557}$), thus these tailored memories can be then employed as examples to build a classifier hardware based on intensity comparison without the need of additional digital transformation layers. Remarkably, this Photonic Emergent Learning platform is not only flexible and fabrication-free, but also relies primarily on analog processes, thus shifting the computational burden of training from the digital layers to the optical domain reducing the computational cost and enhancing performance.