Reservoir computing

Last updated Apr 10, 2022 Edit Source

Reservoir computing is a framework for computation derived from recurrent neural network theory that maps input signals into higher dimensional computational spaces through the dynamics of a fixed, non-linear system called a reservoir. After the input signal is fed into the reservoir, which is treated as a “black box,” a simple readout mechanism is trained to read the state of the reservoir and map it to the desired output

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

• https://en.wikipedia.org/wiki/Echo_state_network
• The ESN is a recurrent neural network with a sparsely connected hidden layer (with typically 1% connectivity)

• #PAPER Next generation reservoir computing (Gauthier 2021)

• https://en.wikipedia.org/wiki/Echo_state_network

• The ESN is a recurrent neural network with a sparsely connected hidden layer (with typically 1% connectivity)

• #PAPER Harnessing nonlinearity: predicting chaotic systems and saving energy in wireless communication (Jaeger 2004)

  • #CODE https://github.com/cknd/pyESN

• #PAPER Design of deep echo state networks (Gallicchio 2018)

  • #CODE https://github.com/lucapedrelli/DeepESN

• #PAPER Using Machine Learning to Replicate Chaotic Attractors and Calculate Lyapunov Exponents from Data (Pathak 2017)

• #PAPER Model-Free Prediction of Large Spatiotemporally Chaotic Systems from Data: A Reservoir Computing Approach (Pathak 2018)

• #PAPER Wind Power Forecasting Based on Echo State Networks and Long Short-Term Memory (Lopez 2018)

  • ESN + LSTM

• #PAPER Comparison between DeepESNs and gatedRNNs on multivariate time-series prediction (Gallicchio 2019)

• #PAPER Deep Echo State Network (DeepESN): A Brief Survey (Gallicchio 2020)

• #PAPER Comparison of Recurrent Neural Networks for Wind Power Forecasting (Lopez 2020)

  • ESN + LSTM