Practical design and performance of physical reservoir computing using hysteresis
By: Yuhei Yamada
Potential Business Impact:
Builds computers from simple magnets and switches.
Physical reservoir computing is an innovative idea for using physical phenomena as computational resources. Recent research has revealed that information processing techniques can improve the performance, but for practical applications, it is equally important to study the level of performance with a simple design that is easy to construct experimentally. We focus on a reservoir composed of independent hysteretic systems as a model suitable for the practical implementation of physical reservoir computing. In this paper, we discuss the appropriate design of this reservoir, its performance, and its limitations. This research will serve as a practical guideline for constructing hysteresis-based reservoirs.
Similar Papers
Practical design and performance of physical reservoir computing using hysteresis
Emerging Technologies
Makes computers learn faster using magnets.
Toward Thermodynamic Reservoir Computing: Exploring SHA-256 ASICs as Potential Physical Substrates
Neural and Evolutionary Computing
Makes old computer chips learn like brains.
Dynamic Reservoir Computing with Physical Neuromorphic Networks
Emerging Technologies
Makes computers learn by using messy circuits.