On Improving The Computing Capacity of Dynamical Systems

Vasileios Athanasiou,Zoran Konkoli

doi:10.1038/s41598-020-65404-3

Abstract

Reservoir Computing has emerged as a practical approach for solving temporal pattern recognition problems. The procedure of preparing the system for pattern recognition is simple, provided that the dynamical system (reservoir) used for computation is complex enough. However, to achieve a sufficient reservoir complexity, one has to use many interacting elements. We propose a novel method to reduce the number of reservoir elements without reducing the computing capacity of the device. It is shown that if an auxiliary input channel can be engineered, the drive, advantageous correlations between the signal one wishes to analyse and the state of the reservoir can emerge, increasing the intelligence of the system. The method has been illustrated on the problem of electrocardiogram (ECG) signal classification. By using a reservoir with only one element, and an optimised drive, more than 93% of the signals have been correctly labelled.

Highlights

Reservoir Computing (RC) has been successfully used for solving plethora of temporal information processing problems, such as speech recognition or time series prediction and classification[1,2,3]
As a source of data, the labelled data set of ECG signals “ECG5000” from the UEA and UCR Time Series Classification Repository[26] is used
Since the reservoir consists of only one memristor element, a simple problem of binary signal classification is investigated

Summary

Introduction

Reservoir Computing (RC) has been successfully used for solving plethora of temporal information processing problems, such as speech recognition or time series prediction and classification[1,2,3]. The drive signal and the feedback (if used) are optimised to achieve maximum input separation, without considering the readout layer.

Results

Conclusion