Machine Learning Without a Processor: Emergent Learning in a Nonlinear Electronic Metamaterial

TL;DR

This paper introduces a nonlinear electronic metamaterial that learns tasks like XOR and nonlinear regression without a computer, offering fast, low-power, and fault-tolerant analog machine learning hardware.

Contribution

It presents the first nonlinear learning metamaterial using self-adjusting nonlinear resistive elements, enabling learning of complex tasks beyond linear systems.

Findings

Learns XOR and nonlinear regression tasks without digital computation.

Reduces training error modes similar to spectral bias in neural networks.

Operates with microsecond speed and picojoule energy dissipation per transistor.

Abstract

Standard deep learning algorithms require differentiating large nonlinear networks, a process that is slow and power-hungry. Electronic learning metamaterials offer potentially fast, efficient, and fault-tolerant hardware for analog machine learning, but existing implementations are linear, severely limiting their capabilities. These systems differ significantly from artificial neural networks as well as the brain, so the feasibility and utility of incorporating nonlinear elements have not been explored. Here we introduce a nonlinear learning metamaterial -- an analog electronic network made of self-adjusting nonlinear resistive elements based on transistors. We demonstrate that the system learns tasks unachievable in linear systems, including XOR and nonlinear regression, without a computer. We find our nonlinear learning metamaterial reduces modes of training error in order (mean, slope, curvature), similar to spectral bias in artificial neural networks. The circuitry is robust to damage, retrainable in seconds, and performs learned tasks in microseconds while dissipating only picojoules of energy across each transistor. This suggests enormous potential for fast, low-power computing in edge systems like sensors, robotic controllers, and medical devices, as well as manufacturability at scale for performing and studying emergent learning.