Short Term Memory and Pattern Matching with Simple Echo State Networks
Two recently proposed approaches to recognize temporal patterns have been proposed by Jäger with the so called Echo State Network (ESN) and by Maass with the so called Liquid State Machine (LSM). The ESN approach assumes a sort of “black-box” operability of the networks and claims a broad applicability to several different problems using the same principle. Here we propose a simplified version of ESNs which we call Simple Echo State Network (SESN) which exhibits good results in memory capacity and pattern matching tasks and which allows a better understanding of the capabilities and restrictions of ESNs.
KeywordsHide Layer Memory Capacity Hide Unit Output Weight Input Weight
Unable to display preview. Download preview PDF.
- 1.Jäger, H.: The ”echo state” approach to analysing and training recurrent neural networks. GMD Report 148, GMD - German National Research Institute for Computer Science (2001)Google Scholar
- 2.Maass, W., Natschläger, T., Markram, H.: Real-time computing without stable states: A new framework for neural computation based on perturbations. Neural Computation 14 (2002)Google Scholar
- 3.Jäger, H.: Short term memory in echo state networks. GMD Report 152, GMD - German National Research Institute for Computer Science (2002)Google Scholar
- 4.Fette, G.: Signalverarbeitung in Neuronalen Netzen vom Typ Echo State Networks diploma thesis (german) (2004)Google Scholar