A novel Reservoir Architecture for Periodic Time Series Prediction

TL;DR

This paper presents a new reservoir computing architecture designed specifically for predicting periodic time series, especially rhythms, with high accuracy and adaptability, outperforming traditional models.

Contribution

The paper introduces a novel reservoir architecture with dynamic parameter tuning and a specialized loss function for improved rhythmic time series prediction.

Findings

Accurate prediction of rhythmic signals within human perception range

Enhanced performance through real-time reservoir tuning

Superior results compared to conventional models

Abstract

This paper introduces a novel approach to predicting periodic time series using reservoir computing. The model is tailored to deliver precise forecasts of rhythms, a crucial aspect for tasks such as generating musical rhythm. Leveraging reservoir computing, our proposed method is ultimately oriented towards predicting human perception of rhythm. Our network accurately predicts rhythmic signals within the human frequency perception range. The model architecture incorporates primary and intermediate neurons tasked with capturing and transmitting rhythmic information. Two parameter matrices, denoted as c and k, regulate the reservoir's overall dynamics. We propose a loss function to adapt c post-training and introduce a dynamic selection (DS) mechanism that adjusts $k$ to focus on areas with outstanding contributions. Experimental results on a diverse test set showcase accurate predictions, further improved through real-time tuning of the reservoir via c and k. Comparative assessments highlight its superior performance compared to conventional models.