A Survey on Reservoir Computing and its Interdisciplinary Applications Beyond Traditional Machine Learning

Abstract

Reservoir computing (RC), first applied to temporal signal processing, is a recurrent neural network in which neurons are randomly connected. Once initialized, the connection strengths remain unchanged. Such a simple structure turns RC into a non-linear dynamical system that maps lowdimensional inputs into a high-dimensional space. The model's rich dynamics, linear separability, and memory capacity then enable a simple linear readout to generate adequate responses for various applications. RC spans areas far beyond machine learning, since it has been shown that the complex dynamics can be realized in various physical hardware implementations and biological devices. This yields greater flexibility and shorter computation time. Moreover, the neuronal responses triggered by the model's dynamics shed light on understanding brain mechanisms that also exploit similar dynamical processes. While the literature on RC is vast and fragmented, here we conduct a unified review of RC's recent developments from machine learning to physics, biology, and neuroscience. We first review the early RC models, and then survey the state-of-the-art models and their applications. We further introduce studies on modeling the brain's mechanisms by RC. Finally, we offer new perspectives on RC development, including reservoir design, coding frameworks unification, physical RC implementations, and interaction between RC, cognitive neuroscience and evolution.

Physical Reservoir Computing Enabled by Solitary Waves and Biologically Inspired Nonlinear Transformation of Input Data

“…[50], it was also demonstrated that the resulting computational scheme does not only circumvent using the matrices of randomly generated neural connections, but is equivalent to and even more computationally efficient than the traditional RC algorithm. This approach was called next-generation reservoir computing [33,[51][52][53][54]. Similar algorithms that further improve the performance of RC systems have also been proposed [55].…”

Reservoir computing using spin-VCSELs - the influence of timescales and data injection schemes

“…Liquid State Machine [3] and Echo State Network [4], and later on unified under the name RC [5]. A review about the history and recent developments of RC is given by Zhang et al [6]. Due to their fast data processing and the relatively simple data injection and readout schemes, optical systems are especially suited and a variety of different optical RC implementations have already been proposed, theoretically investigated and experimentally realized [7,8].…”

Reservoir Computing Using Measurement-Controlled Quantum Dynamics

“…Reservoir computing (RC) is a resource-efficient neuromorphic information processing algorithm that is especially suitable for making forecasts of highly nonlinear and chaotic time series that underpin a number of essential natural and human-made phenomena, including the variation of climate, dynamics of Earth population, trends in financial markets, energy generation, and drug discovery [12,[20][21][22][23][24][25][26][27]. A typical RC algorithm [20,21] employs a randomly initialised task-dependent neural network (reservoir) that is connected to the input units through random connections.…”