• Publications
  • Influence
The''echo state''approach to analysing and training recurrent neural networks
TLDR
The report introduces a constructive learning algorithm for recurrent neural networks, which modifies only the weights to output units in order to achieve the learning task. Expand
  • 1,535
  • 381
  • PDF
Harnessing Nonlinearity: Predicting Chaotic Systems and Saving Energy in Wireless Communication
TLDR
We present a method for learning nonlinear systems, echo state networks (ESNs). Expand
  • 2,033
  • 194
  • PDF
Reservoir computing approaches to recurrent neural network training
TLDR
Echo State Networks and Liquid State Machines introduced a new paradigm in artificial recurrent neural network (RNN) training, where an RNN (the reservoir) is generated randomly and only a readout is trained. Expand
  • 1,340
  • 146
  • PDF
Adaptive Nonlinear System Identification with Echo State Networks
  • H. Jaeger
  • Mathematics, Computer Science
  • NIPS
  • 2002
TLDR
This article reviews the basic ideas and describes an online adaptation scheme based on the RLS algorithm known from adaptive linear systems. Expand
  • 488
  • 49
  • PDF
Optimization and applications of echo state networks with leaky- integrator neurons
TLDR
We present stability conditions, introduce and investigate a stochastic gradient descent method for the optimization of the global learning parameters (input and output feedback scalings, leaking rate, spectral radius) and demonstrate the usefulness of leaky-integrator ESNs for learning very slow dynamic systems. Expand
  • 533
  • 39
  • PDF
Observable Operator Models for Discrete Stochastic Time Series
  • H. Jaeger
  • Mathematics, Medicine
  • Neural Computation
  • 1 June 2000
TLDR
This article provides a novel, simple characterization of linearly dependent processes, called observable operator models. Expand
  • 196
  • 36
  • PDF
Re-visiting the echo state property
TLDR
We use analytical examples to show that a widely used criterion for the ESP, the spectral radius of the weight matrix being smaller than unity, is not sufficient to satisfy the echo state property. Expand
  • 209
  • 17
  • PDF
Controlling Recurrent Neural Networks by Conceptors
TLDR
The human brain is a dynamical system whose extremely complex sensor-driven neural processes give rise to conceptual, logical cognition. Expand
  • 78
  • 16
  • PDF
Long Short-Term Memory in Echo State Networks: Details of a Simulation Study
TLDR
We expose ESNs to a series of synthetic benchmark tasks that have been used in the literature to study the learnability of long-range temporal dependencies. Expand
  • 45
  • 12
  • PDF
Echo state network
  • H. Jaeger
  • Computer Science, Physics
  • Scholarpedia
  • 6 September 2007
  • 197
  • 11