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

Autor(es)

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

Afiliação do(s) autor(es)

^[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

• Tipo de documento: Artigo Científico
• Fonte: NEURAL NETWORKS; v. 124, p. 158-169, APR 2020.
• Citações Web of Science: 0

Resumo

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)

• Processo FAPESP: 15/50122-0 - Fenômenos dinâmicos em redes complexas: fundamentos e aplicações
• Beneficiário: Elbert Einstein Nehrer Macau
• Linha de fomento: Auxílio à Pesquisa - Temático