Towards Deep Physical Reservoir Computing Through Automatic Task Decomposition And Mapping
This addresses the problem of scaling photonic reservoir computing for low-energy, high-bandwidth applications, representing an incremental advancement in training methods for multi-reservoir systems.
The paper tackles the challenge of training multi-reservoir systems, such as photonic reservoir computing, where backpropagation is not directly applicable, by proposing an alternative method using backpropagation-derived intermediate targets; it demonstrates feasibility by training a network of 3 Echo State Networks on the NARMA-10 task, indicating efficient training.
Photonic reservoir computing is a promising candidate for low-energy computing at high bandwidths. Despite recent successes, there are bounds to what one can achieve simply by making photonic reservoirs larger. Therefore, a switch from single-reservoir computing to multi-reservoir and even deep physical reservoir computing is desirable. Given that backpropagation can not be used directly to train multi-reservoir systems in our targeted setting, we propose an alternative approach that still uses its power to derive intermediate targets. In this work we report our findings on a conducted experiment to evaluate the general feasibility of our approach by training a network of 3 Echo State Networks to perform the well-known NARMA-10 task using targets derived through backpropagation. Our results indicate that our proposed method is well-suited to train multi-reservoir systems in a efficient way.