Unsupervised learning of echo state networks: balancing the double pole

A possible alternative to fine topology tuning for Neural Network (NN) optimization is to use Echo State Networks (ESNs), recurrent NNs built upon a large reservoir of sparsely randomly connected neurons. The promises of ESNs have been fulfilled for supervised learning tasks, but unsupervised learning tasks, such as control problems, require more flexible optimization methods. We propose here to apply stateof-the-art methods in evolutionary continuous parameter optimization, to the evolutionary learning of ESN. First, a standard supervised learning problem is used to validate our approach and compare it to the standard quadratic one. The classical double pole balancing control problem is then used to demonstrate that unsupervised evolutionary learning of ESNs yields results that compete with the best topologylearning methods. Categories and Subject Descriptors I.2.6 [Artificial Intelligence]: Learning—Connectionism and neural nets General Terms Algorithms, Design Keywords Echo S...

• Type: Conference
• Year: 2008
• Where: GECCO
• Authors: Fei Jiang, Hugues Berry, Marc Schoenauer
• Keywords: Echo State Networks, Evolutionary Learning, GECCO 2008, Optimization, Supervised Learning