Time delay systems for reservoir computing
Ortín, Silvia; Pesquera, Luis; Van der Sande, Guy; Soriano, Miguel C.
Photonic Reservoir Computing: Optical Recurrent Neural Networks, De Gruyter, 117-151 (2019)
Photonic Reservoir Computing: Optical Recurrent Neural Networks, De Gruyter, 117-151 (2019)
Delay-based reservoir computers are reservoir computing implementations based on dynamical systems with delay. The dynamical system is often a single nonlinear node. As it will be explained later in more detail, delay-based reservoir computers assign different time-slots of the nonlinear node response to different network nodes, also known as virtual nodes. This time multiplexing of a single nonlinear node’s response is equivalent to having a distributed set of virtual nodes along the delayed feedback loop.
Related research projects
IDEA
Improving data DEcoding in optical communication networks All-optically using neuro-inspired photonic systems
I.P.: Miguel C. Soriano, Ingo Fischer, Claudio Mirasso
Novel technologies related to optical communications, sensing, the Internet of Things (IoT) and artificial intelligence have been generating unique opportunities and potential to enhance our quality-of-life, and to provide new services for …