Performance boost of time-delay reservoir computing by non-resonant clock cycle
arXiv:1905.02534 · doi:10.1016/j.neunet.2020.01.010
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.
References in corpus (3)
Cited by in corpus (11)
- Reservoir Computing with Diverse Timescales for Prediction of Multiscale Dynamics
- Deep Neural Networks using a Single Neuron: Folded-in-Time Architecture using Feedback-Modulated Delay Loops
- Insight into Delay Based Reservoir Computing via Eigenvalue Analysis
- Limitations of the recall capabilities in delay based reservoir computing systems
- Reservoir Computers with Random and Optimized Time-Shifts
- Experimental demonstration of bandwidth enhancement in photonic time delay reservoir computing
- Laminar chaos in systems with quasiperiodic delay
- Time-shift selection for reservoir computing using a rank-revealing QR algorithm
- Emulating complex networks with a single delay differential equation
- Exploring Non-Steady-State Charge Transport Dynamics in Information Processing: Insights from Reservoir Computing
- 56 GBaud PAM-4 100 km Transmission System with Photonic Processing Schemes