Evolino for recurrent support vector machines

Abstract. We introduce a new class of recurrent, truly sequential SVM-like devices with internal adaptive states, trained by a novel method called EVOlution of systems with KErnel-based outputs (Evoke), an instance of the recent Evolino class of methods. Evoke evolves recurrent networks to detect and represent temporal dependencies while using SVM to produce precise outputs. Evoke is the first SVM-based mechanism learning to classify a context-sensitive language. It also outperforms recent state-of-the-art gradient-based recurrent neural networks (RNNs) on various time series prediction tasks.

• Type: Conference
• Year: 2006
• Where: ESANN
• Authors: Jürgen Schmidhuber, Matteo Gagliolo, Daan Wierstra, Faustino J. Gomez
• Keywords: ESANN 2006, ESANN 2007, Recurrent Networks, Recurrent Neural Networks, Sequential Svm-like Devices