Hybrid Magnonic Reservoir Computing
This work addresses the need for faster and lower-power computing systems in machine learning, though it appears incremental as it builds on established magnonic reservoir designs.
The paper tackled the problem of improving physical reservoir computing for machine learning by introducing hybrid designs combining magnonic systems with neural networks, and showed that these designs perform comparably or better than traditional dense neural networks on various real-world datasets.
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.