Limitations of the recall capabilities in delay based reservoir computing systems

Abstract

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

References in corpus (7)

• Optoelectronic Reservoir Computing
• High performance photonic reservoir computer based on a coherently driven passive cavity
• Tutorial: Photonic Neural Networks in Delay Systems
• Online Training of an Opto-Electronic Reservoir Computer Applied to Real-Time Channel Equalisation
• Machine learning algorithms for predicting the amplitude of chaotic laser pulses
• Performance boost of time-delay reservoir computing by non-resonant clock cycle
• Reservoir computing with simple oscillators: Virtual and real networks

Cited by in corpus (4)

• Insight into Delay Based Reservoir Computing via Eigenvalue Analysis
• Learning Continuous Chaotic Attractors with a Reservoir Computer
• Feedback induced locking in semiconductor lasers with strong amplitude-phase coupling
• Engineering Quantum Reservoirs through Krylov Complexity, Expressivity and Observability