Techniques for Enhancing Memory Capacity of Reservoir Computing

TL;DR

This paper introduces novel methods to enhance the memory capacity of reservoir computing models, such as ESN and CBM-RC, by modifying network configurations without altering internal reservoir dynamics, improving time series processing.

Contribution

The study proposes three new techniques—Delay, Pass through, and Clustering—to increase memory capacity in reservoir models while maintaining nonlinearity, tested on ESN and CBM-RC.

Findings

Delay method improves memory retention in RC models.

Pass through method simplifies input-output mapping.

Clustering method enhances information processing capacity.

Abstract

Reservoir Computing (RC) is a bio-inspired machine learning framework, and various models have been proposed. RC is a well-suited model for time series data processing, but there is a trade-off between memory capacity and nonlinearity. In this study, we propose methods to improve the memory capacity of reservoir models by modifying their network configuration except for the inside of reservoirs. The Delay method retains past inputs by adding delay node chains to the input layer with the specified number of delay steps. To suppress the effect of input value increase due to the Delay method, we divide the input weights by the number of added delay steps. The Pass through method feeds input values directly to the output layer. The Clustering method divides the input and reservoir nodes into multiple parts and integrates them at the output layer. We applied these methods to an echo state network (ESN), a typical RC model, and the chaotic Boltzmann machine (CBM)-RC, which can be efficiently implemented in integrated circuits. We evaluated their performance on the NARMA task, and measured information processing capacity (IPC) to evaluate the trade-off between memory capacity and nonlinearity.