reservoir computing

"Reservoir computing is a framework for computation that may be viewed as an extension of neural networks.^[1] Typically an input signal is fed into a fixed (random) dynamical system called a reservoir and the dynamics of the reservoir map the input to a higher dimension. Then a simple readout mechanism is trained to read the state of the reservoir and map it to the desired output. The main benefit is that the training is performed only at the readout stage and the reservoir is fixed. Liquid-state machines ^[2] and echo state networks ^[3] are two major types of reservoir computing.

Types of reservoir computing are:

Context reverberation network

An early example of reservoir computing was the context reverberation network .^[5] In this architecture, an input layer feeds into a high dimensional dynamical system which is read out by a trainable single-layer perceptron. Two kinds of dynamical system were described: a recurrent neural network with fixed random weights, and a continuous reaction-diffusion system inspired by Alan Turing’s model of morphogenesis. At the trainable layer, the perceptron associates current inputs with the signals that reverberate in the dynamical system; the latter were said to provide a dynamic "context" for the inputs. In the language of later work, the reaction-diffusion system served as the reservoir.

Echo state network

Main article: Echo state network

Backpropagation-decorrelation

Backpropagation-Decorrelation (BPDC)

Liquid-state machine

Main article: Liquid-state machine

Reservoir Computing for Structured Data

The Tree Echo State Network ^[6] (TreeESN) model represents a generalization of the Reservoir Computing framework to tree structured data.


http://reservoir-computing.org/

https://en.wikipedia.org/wiki/Reservoir_computing

https://www.researchgate.net/publication/221166209_An_overview_of_reservoir_computing_Theory_applications_and_implementations



TOOLS

Oger - http://organic.elis.ugent.be/oger