OscNet: Machine Learning on CMOS Oscillator Networks

TL;DR

OscNet introduces an energy-efficient CMOS oscillator network framework inspired by biological neural processes, achieving competitive machine learning performance with reduced energy consumption.

Contribution

This paper presents a novel CMOS oscillator network architecture implementing Hebbian learning for energy-efficient machine learning, inspired by biological neural systems.

Findings

OscNet achieves comparable or better performance than traditional algorithms.

The Hebbian learning pipeline is energy-efficient and biologically plausible.

Simulation results validate the effectiveness of OscNet architectures.

Abstract

Machine learning and AI have achieved remarkable advancements but at the cost of significant computational resources and energy consumption. This has created an urgent need for a novel, energy-efficient computational fabric to replace the current computing pipeline. Recently, a promising approach has emerged by mimicking spiking neurons in the brain and leveraging oscillators on CMOS for direct computation. In this context, we propose a new and energy efficient machine learning framework implemented on CMOS Oscillator Networks (OscNet). We model the developmental processes of the prenatal brain's visual system using OscNet, updating weights based on the biologically inspired Hebbian rule. This same pipeline is then directly applied to standard machine learning tasks. OscNet is a specially designed hardware and is inherently energy-efficient. Its reliance on forward propagation alone for training further enhances its energy efficiency while maintaining biological plausibility. Simulation validates our designs of OscNet architectures. Experimental results demonstrate that Hebbian learning pipeline on OscNet achieves performance comparable to or even surpassing traditional machine learning algorithms, highlighting its potential as a energy efficient and effective computational paradigm.