Reservoir Computing Speeds Up

Abstract

Reservoir computing, originally referred to as an echo state network or a liquid state machine, is a braininspired paradigm for processing temporal information. It involves learning a "read-out" interpretation for nonlinear transients developed by high-dimensional dynamics when the latter is excited by the information signal to be processed. This novel computational paradigm is derived from recurrent neural network and machine learning techniques. It has recently been implemented in photonic hardware for a dynamical system, which opens the path to ultrafast brain-inspired computing. We report on a novel implementation involving an electro-optic phase-delay dynamics designed with off-the-shelf optoelectronic telecom devices, thus providing the targeted wide bandwidth. Computational efficiency is demonstrated experimentally with speech-recognition tasks. State-of-the-art speed performances reach one million words per second, with very low word error rate. Additionally, to record speed processing, our investigations have revealed computing-efficiency improvements through yet-unexplored temporalinformation-processing techniques, such as simultaneous multisample injection and pitched sampling at the read-out compared to information "write-in".

Electroactive polymer gels as probabilistic reservoir automata for computation

“…A reservoir in this context must be made up of individual, non-linear units, and capable of storing information 64 much like the PMA has already presented. In the field of physical computing, reservoirs produce multiple outputs to provide a rich non-linear in interaction with the surrounding environment.…”

“…Although most examples of reservoirs in morphological computing are physical, like the gel, they can also be represented virtually. 64 Virtual reservoirs can take the form of modeled systems, such as artificial neural networks, or as a database of responses from physical reservoirs. The discretized probabilistic automata transitions from the previous section, as shown in Figure 5 , have potential as a virtual database reservoir that can be used to validate the EAP hydrogel PMA as a reservoir computer.…”

Bridging the Band Gap: What Device Physicists Need to Know About Machine Learning

“…A reservoir computer (RC) builds upon several RNN models and so is also suited for temporal data processing. The reservoir part of a RC is treated as a black box, but has two requirements: it must be made up of individual nonlinear units and be able to store information [160]. A RC uses the reservoir to map inputs into a higher dimensional computing space, and then conducts pattern analysis in a readout section.…”