Machine Learning with Chaotic Strange Attractors
This addresses the unsustainable power demands in machine learning for researchers and practitioners, offering a novel low-power alternative.
The paper tackles the high power consumption of machine learning by introducing an analog computing method that uses chaotic strange attractors, achieving performance comparable to current techniques while requiring only milliwatt-scale power levels.
Machine learning studies need colossal power to process massive datasets and train neural networks to reach high accuracies, which have become gradually unsustainable. Limited by the von Neumann bottleneck, current computing architectures and methods fuel this high power consumption. Here, we present an analog computing method that harnesses chaotic nonlinear attractors to perform machine learning tasks with low power consumption. Inspired by neuromorphic computing, our model is a programmable, versatile, and generalized platform for machine learning tasks. Our mode provides exceptional performance in clustering by utilizing chaotic attractors' nonlinear mapping and sensitivity to initial conditions. When deployed as a simple analog device, it only requires milliwatt-scale power levels while being on par with current machine learning techniques. We demonstrate low errors and high accuracies with our model for regression and classification-based learning tasks.