Cliff B. Abbott

Cliff B. Abbott, Mark Elo, Dmytro A. Bozhko

We introduce Perturbative Gradient Training (PGT), a novel training paradigm that overcomes a critical limitation of physical reservoir computing: the inability to perform backpropagation due to the black-box nature of physical reservoirs. Drawing inspiration from perturbation theory in physics, PGT uses random perturbations in the network's parameter space to approximate gradient updates using only forward passes. We demonstrate the feasibility of this approach on both simulated neural network architectures, including a dense network and a transformer model with a reservoir layer, and on experimental hardware using a magnonic auto-oscillation ring as the physical reservoir. Our results show that PGT can achieve performance comparable to that of standard backpropagation methods in cases where backpropagation is impractical or impossible. PGT represents a promising step toward integrating physical reservoirs into deeper neural network architectures and achieving significant energy efficiency gains in AI training.

Cliff B. Abbott, Dmytro A. Bozhko

Magnonic systems have been a major area of research interest due to their potential benefits in speed and lower power consumption compared to traditional computing. One particular area that they may be of advantage is as Physical Reservoir Computers in machine learning models. In this work, we build on an established design for using an Auto-Oscillation Ring as a reservoir computer by introducing a simple neural network midstream and introduce an additional design using a spin wave guide with a scattering regime for processing data with different types of inputs. We simulate these designs on the new micro magnetic simulation software, Magnum.np, and show that the designs are capable of performing on various real world data sets comparably or better than traditional dense neural networks.