Abstract
Reservoir computing is a neuromorphic computing scheme inspired by the human brain. It has found great success as a versatile hardware-compatible application of machine learning concepts. In this paper, we highlight the fundamental working principles and important characteristics of reservoir computing with a particular focus on photonic systems and networks. These systems can further be enhanced by the inclusion of delayed variables to produce complex spatiotemporally mixed “time-multiplexed” networks. We use a simple nonlinear oscillator model, that is not only applicable to lasers, but can also describe a variety of other oscillating systems.
Highlights
M ACHINE learning is a quickly expanding field
Reservoir computing is one particular set of machine learning rules that is compatible with non-standard hardware
This paper focuses on reservoir computing in laser networks
Summary
M ACHINE learning is a quickly expanding field. It deals with concepts inspired by the human brain and features abstracted versions of neurons and synapses, which are trained to fulfil a specific task. Contemporary reservoir computing prototypes typically posses a lot fewer nodes than state-of-the-art deep learning neural networks. This is partially based on the experimental nature, where read-out procedures often represent a bottle-neck, but is due to the relative novelty of this subfield. [4] argues, many of the current record breaking architectures in artificial neural networks profit from the increased availability of powerful GPUs, allowing for the efficient simulation of large networks. By their nature reservoir computers will make less efficient use of every node than a fully trained recurrent network.
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: IEEE Journal of Selected Topics in Quantum Electronics
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
