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

arXiv:2311.00537v2 Announce Type: replace-cross
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 …

abstract algorithms analog arxiv capabilities cond-mat.soft cs.et cs.lg deep learning deep learning algorithms electronic hardware linear machine machine learning networks power process processor standard systems type