Monadic Pavlovian associative learning in a backpropagation-free photonic network

TL;DR

This paper introduces a novel backpropagation-free associative learning method implemented on a photonic platform, enabling faster and more energy-efficient AI training through monadic Pavlovian hardware.

Contribution

It demonstrates a scalable photonic circuit for Pavlovian associative learning without backpropagation, advancing energy-efficient AI hardware.

Findings

Successful experimental realization of monadic Pavlovian learning on photonic hardware.

Scalable photonic circuit network for associative learning tasks.

Enhanced speed and bandwidth compared to traditional neural network training.

Abstract

Over a century ago, Ivan P. Pavlov, in a classic experiment, demonstrated how dogs can learn to associate a ringing bell with food, thereby causing a ring to result in salivation. Today, it is rare to find the use of Pavlovian type associative learning for artificial intelligence (AI) applications even though other learning concepts, in particular backpropagation on artificial neural networks (ANNs) have flourished. However, training using the backpropagation method on 'conventional' ANNs, especially in the form of modern deep neural networks (DNNs), is computationally and energy intensive. Here we experimentally demonstrate a form of backpropagation-free learning using a single (or monadic) associative hardware element. We realize this on an integrated photonic platform using phase-change materials combined with on-chip cascaded directional couplers. We then develop a scaled-up circuit network using our monadic Pavlovian photonic hardware that delivers a distinct machine-learning framework based on single-element associations and, importantly, using backpropagation-free architectures to address general learning tasks. Our approach reduces the computational burden imposed by learning in conventional neural network approaches, thereby increasing speed, whilst also offering higher bandwidth inherent to our photonic implementation.