Reservoir Computing Using Complex Systems
This work addresses the challenge of optimizing physical systems for machine learning tasks, but it is incremental as it builds on existing reservoir computing methods with specific hardware improvements.
The paper tackled the problem of improving computational capability in physical reservoir computing by using a memristive chaotic oscillator as a single-node reservoir, resulting in optimized hyperparameters that enhanced performance on non-temporal tasks like polynomial approximation and chaotic trajectory prediction.
Reservoir Computing is an emerging machine learning framework which is a versatile option for utilising physical systems for computation. In this paper, we demonstrate how a single node reservoir, made of a simple electronic circuit, can be employed for computation and explore the available options to improve the computational capability of the physical reservoirs. We build a reservoir computing system using a memristive chaotic oscillator as the reservoir. We choose two of the available hyperparameters to find the optimal working regime for the reservoir, resulting in two reservoir versions. We compare the performance of both the reservoirs in a set of three non-temporal tasks: approximating two non-chaotic polynomials and a chaotic trajectory of the Lorenz time series. We also demonstrate how the dynamics of the physical system plays a direct role in the reservoir's hyperparameters and hence in the reservoir's prediction ability.