Limitations of the recall capabilities in delay based reservoir computing systems
This work addresses limitations in recall capabilities for delay-based reservoir computing systems, which is incremental for researchers in neuromorphic computing and signal processing.
The paper analyzes the memory capacity of a delay-based reservoir computing system using a Hopf normal form nonlinearity, finding that total memory capacity depends on the ratio between input period and time delay, with optimal performance at a time delay about 1.6 times the clock cycle.
We analyze the memory capacity of a delay based reservoir computer with a Hopf normal form as nonlinearity and numerically compute the linear as well as the higher order recall capabilities. A possible physical realisation could be a laser with external cavity, for which the information is fed via electrical injection. A task independent quantification of the computational capability of the reservoir system is done via a complete orthonormal set of basis functions. Our results suggest that even for constant readout dimension the total memory capacity is dependent on the ratio between the information input period, also called the clock cycle, and the time delay in the system. Optimal performance is found for a time delay about 1.6 times the clock cycle