Modeling systems with internal state using evolino

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. Categories and Subject Descriptors I.2.6 [Artificial Intelligence]: Learning—Connectionism and neural nets General Terms Experimentation, Performance, Algorithms Keywords Time-series prediction, Recurrent Neural Networks, Evolution and Learning

• Type: Conference
• Year: 2005
• Where: GECCO
• Authors: Daan Wierstra, Faustino J. Gomez, Jürgen Schmidhuber
• Keywords: GECCO 2005, Optimal Linear Mapping, Recurrent Neural Networks, RNN Hidden Node