论文信息 - The''echo state''approach to analysing and training recurrent neural networks

The''echo state''approach to analysing and training recurrent neural networks

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. key words: recurrent neural networks, supervised learning Zusammenfassung. Der Report führt ein konstruktives Lernverfahren für rekurrente neuronale Netze ein, welches zum Erreichen des Lernzieles lediglich die Gewichte der zu den Ausgabeneuronen führenden Verbindungen modifiziert. Stichwörter: rekurrente neuronale Netze, überwachtes Lernen

Herbert Jaeger | H. Jaeger

[1] Barak A. Pearlmutter. Gradient calculations for dynamic recurrent neural networks: a survey , 1995, IEEE Trans. Neural Networks.

[2] D. Broomhead,et al. Takens embedding theorems for forced and stochastic systems , 1997 .

[3] Snehasis Mukhopadhyay,et al. Adaptive control using neural networks and approximate models , 1997, IEEE Trans. Neural Networks.

[4] Masahiro Kimura,et al. Learning dynamical systems by recurrent neural networks from orbits , 1998, Neural Networks.

[5] James McNames,et al. Innovations in local modeling for time series prediction , 1999 .

[6] B. Farhang-Boroujeny,et al. Adaptive Filters: Theory and Applications , 1999 .

[7] Jürgen Schmidhuber,et al. Learning to Forget: Continual Prediction with LSTM , 2000, Neural Computation.

[8] L. Abbott,et al. Synaptic plasticity: taming the beast , 2000, Nature Neuroscience.

[9] Local Modeling Optimization for Time Series Prediction , 2000 .

[10] Amir F. Atiya,et al. New results on recurrent network training: unifying the algorithms and accelerating convergence , 2000, IEEE Trans. Neural Networks Learn. Syst..

[11] Jürgen Schmidhuber,et al. Applying LSTM to Time Series Predictable through Time-Window Approaches , 2000, ICANN.

[12] Henry Markram,et al. Real-Time Computing Without Stable States: A New Framework for Neural Computation Based on Perturbations , 2002, Neural Computation.