Reservoir Computing Trends

By Mantas Lukosevicius, Herbert Jaeger, Benjamin Schrauwen. KI - Künstliche Intelligenz, 2012

383 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Cognitive Neuroscience, Electrical and Electronic Engineering

View Paper: https://www.semanticscholar.org/paper/219b27d719118d7a65f4f422608800cd5490efb7

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Cognitive Neuroscience

In Electrical and Electronic Engineering

Citations in the corpus

Physical reservoir computing—an introductory perspective (2020, background): “RC is a framework for recurrent neural network (RNN) training and was proposed in the early 2000s as a broad concept that allows to deal with a number of different models of RNN, including the echo-state network (ESN) [1–3] and the liquid state machine (LSM) [4], under the same umbrella [5–8].”
Recent Advances in Physical Reservoir Computing: A Review (2018, methodology): “Specifically, RC is a unified computational framework (Lukoševičius & Jaeger, 2009; Verstraeten, Schrauwen, d’ Haene, & Stroobandt, 2007), derived from independently proposed RNN models, such as echo state networks (ESNs) (Jaeger, 2001) and liquid state machines (LSMs) (Maass, Natschläger, & Markram”
Colloquium: Criticality and dynamical scaling in living systems (2017, background): “In artificial intelligence, criticality is exploited in socalled “reservoir computing” (Lukoševičius et al., 2012) that was developed independently in the fields of machine learning (“echo state networks” of Jaeger (2007)) and computational neuroscience (“liquid state machine” in Maass et al.…”
All-optical Reservoir Computing (2012, background): “It is very well suited to process time dependent inputs, and provides state-of-the-art performance on tasks such as speech recognition, time series prediction, etc. (see [11,15] for reviews).”
A Practical Guide to Applying Echo State Networks (2012, background): “RC is currently a prolific research area, giving important insights into RNNs, procuring practical machine learning tools, as well as enabling computation with non-conventional hardware [16].”
Deep Learning with Long Short-Term Memory Networks for Diagnosing Faults in Smart Grids (2021, background): “It is well studied that the application of RNNs has been started with LSMs and ESNs, where the former is originated from computational neuroscience and the latter has come from the field of machine learning.”
At the Edge of Chaos: How Cerebellar Granular Layer Network Dynamics Can Provide the Basis for Temporal Filters (2015, methodology): “These capabilities have been applied to a range of problems such as robot motor control that are thought to involve the cerebellum in their biological equivalents [21].”
Acoustic Modeling With Hierarchical Reservoirs (2013, background): “With (this guarantees a stable recurrent network as shown in [20]–[23]), one obtains that”