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

Understand

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.