Modeling systems with internal state using evolino

Authors:
Daan Wierstra;Faustino J. Gomez;Jürgen Schmidhuber
Affiliations:
IDSIA, Lugano, Switzerland;IDSIA, Lugano, Switzerland;IDSIA, Lugano, Switzerland and TU Munich, München, Germany
Venue:
GECCO '05 Proceedings of the 7th annual conference on Genetic and evolutionary computation
Year:
2005

Citing 12
Cited 4

Learning and evolution in neural networks

Adaptive Behavior
Efficient reinforcement learning through symbiotic evolution

Machine Learning - Special issue on reinforcement learning
Long short-term memory

Neural Computation
Evolutionary Neural Networks for Nonlinear Dynamics Modeling

PPSN V Proceedings of the 5th International Conference on Parallel Problem Solving from Nature
Solving Non-Markovian Control Tasks with Neuro-Evolution

IJCAI '99 Proceedings of the Sixteenth International Joint Conference on Artificial Intelligence
Learning to Forget: Continual Prediction with LSTM

Neural Computation
Evolutionary induction of sparse neural trees

Evolutionary Computation
Evolino: hybrid neuroevolution / optimal linear search for sequence learning

IJCAI'05 Proceedings of the 19th international joint conference on Artificial intelligence
Cooperative-competitive genetic evolution of radial basis function centers and widths for time series prediction

IEEE Transactions on Neural Networks
A new evolutionary system for evolving artificial neural networks

IEEE Transactions on Neural Networks
Combined genetic algorithm optimization and regularized orthogonal least squares learning for radial basis function networks

IEEE Transactions on Neural Networks
LSTM recurrent networks learn simple context-free and context-sensitive languages

IEEE Transactions on Neural Networks

Training Recurrent Networks by Evolino

Neural Computation
2007 Special Issue: Decoupled echo state networks with lateral inhibition

Neural Networks
Predictive Modeling with Echo State Networks

ICANN '08 Proceedings of the 18th international conference on Artificial Neural Networks, Part I
Dynamic Factor Graphs for Time Series Modeling

ECML PKDD '09 Proceedings of the European Conference on Machine Learning and Knowledge Discovery in Databases: Part II

Quantified Score

Hi-index	0.00

Visualization

Abstract

Existing Recurrent Neural Networks (RNNs) are limited in their ability to model dynamical systems with nonlinearities and hidden internal states. Here we use our general framework for sequence learning, EVOlution of recurrent systems with LINear Outputs (Evolino), to discover good RNN hidden node weights through evolution, while using linear regression to compute an optimal linear mapping from hidden state to output. Using the Long Short-Term Memory RNN Architecture, Evolino outperforms previous state-of-the-art methods on several tasks: 1) context-sensitive languages, 2) multiple superimposed sine waves.