Design of Oscillatory Neural Networks by Machine Learning

TL;DR

This paper presents a machine learning-based approach to designing Oscillatory Neural Networks, enabling improved performance and simplified circuit topology for associative memories and classifiers.

Contribution

It introduces a novel machine learning methodology, using BPTT, for designing ONNs with superior performance and simpler circuits compared to traditional methods.

Findings

Machine learning-designed ONNs outperform Hebbian-based designs.

Multi-layered ONNs show better performance than single-layer ones.

Designs enable significant circuit simplifications.

Abstract

We demonstrate the utility of machine learning algorithms for the design of Oscillatory Neural Networks (ONNs). After constructing a circuit model of the oscillators in a machine-learning-enabled simulator and performing Backpropagation through time (BPTT) for determining the coupling resistances between the ring oscillators, we show the design of associative memories and multi-layered ONN classifiers. The machine-learning-designed ONNs show superior performance compared to other design methods (such as Hebbian learning) and they also enable significant simplifications in the circuit topology. We demonstrate the design of multi-layered ONNs that show superior performance compared to single-layer ones. We argue Machine learning can unlock the true computing potential of ONNs hardware.