Performance boost of time-delay reservoir computing by non-resonant clock cycle

Author(s)

Stelzer, Florian ^{[1, 2]} ; Roehm, Andre ^{[3, 4]} ; Luedge, Kathy ^[3] ; Yanchuk, Serhiy ^[1]

Affiliation

^[1] Tech Univ Berlin, Inst Math, D-10623 Berlin - Germany

^[2] Humboldt Univ, Dept Math, D-12489 Berlin - Germany

^[3] Tech Univ Berlin, Inst Theoret Phys, D-10623 Berlin - Germany

^[4] UIB, IFISC, CSIC, Campus Univ Illes Balears, E-07122 Palma De Mallorca - Spain

• Document type: Journal article
• Source: NEURAL NETWORKS; v. 124, p. 158-169, APR 2020.
• Web of Science Citations: 0

Abstract

The time-delay-based reservoir computing setup has seen tremendous success in both experiment and simulation. It allows for the construction of large neuromorphic computing systems with only few components. However, until now the interplay of the different timescales has not been investigated thoroughly. In this manuscript, we investigate the effects of a mismatch between the time-delay and the clock cycle for a general model. Typically, these two time scales are considered to be equal. Here we show that the case of equal or resonant time-delay and clock cycle could be actively detrimental and leads to an increase of the approximation error of the reservoir. In particular, we can show that non-resonant ratios of these time scales have maximal memory capacities. We achieve this by translating the periodically driven delay-dynamical system into an equivalent network. Networks that originate from a system with resonant delay-times and clock cycles fail to utilize all of their degrees of freedom, which causes the degradation of their performance. (C) 2020 The Authors. Published by Elsevier Ltd. (AU)

• FAPESP's process: 15/50122-0 - Dynamic phenomena in complex networks: basics and applications
• Grantee: Elbert Einstein Nehrer Macau
• Support Opportunities: Research Projects - Thematic Grants