2019/05/31 by Florian Stelzer, André Röhm, Kathy Lüdge +1 · 69 citations
Computer Science · Engineering · Mathematics · Physics and Astronomy · #Advanced Memory and Neural Computing #Artificial intelligence #Artificial neural network #Computer science #Control theory (sociology) #Degradation (telecommunications) #Neural Networks and Reservoir Computing #Neuromorphic engineering #Nonlinear Dynamics and Pattern Formation #Propagation delay #Recurrent neural network #Reservoir computing #Telecommunications #cs.LG #cs.NE #math.DS #nlin.AO
paper · pdf · doi:10.1016/j.neunet.2020.01.010
published in Neural Networks 124, 158-169 (Elsevier BV)
openalex publication_date 2020/01/15 · arxiv created 2020/01/23 · arxiv updated 2021/08/09 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/06
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.