Studies on reservoir initialization and dynamics shaping in echo state networks

Joschka Boedecker, Oliver Obst, N. Michael Mayer, Minoru Asada

Research output: Chapter in Book / Conference PaperConference Paperpeer-review

15 Citations (Scopus)

Abstract

![CDATA[The fixed random connectivity of networks in reservoir computing leads to significant variation in performance. Only few problem specific optimization procedures are known to date. We study a general initialization method using permutation matrices and derive a new unsupervised learning rule based on intrinsic plasticity (IP) for echo state networks. Using three different benchmarks, we show that networks with permutation matrices for the reservoir connectivity have much longer memory than the other methods, but are also able to perform highly non-linear mappings. We also show that IP based on sigmoid transfer functions is limited concerning the output distributions that can be achieved.]]
Original languageEnglish
Title of host publicationESANN'2009 Proceedings: 17th European Symposium on Artificial Networks: Advances in Computational Intelligence and Learning, Bruges, Belgium, 22-24 April 2009
Publisherd-side
Pages227-232
Number of pages6
ISBN (Print)9782930307091
Publication statusPublished - 2009
EventEuropean Symposium on Artificial Neural Networks -
Duration: 22 Apr 2009 → …

Conference

ConferenceEuropean Symposium on Artificial Neural Networks
Period22/04/09 → …

Keywords

  • neural networks (computer science)
  • reservoir computing

Fingerprint

Dive into the research topics of 'Studies on reservoir initialization and dynamics shaping in echo state networks'. Together they form a unique fingerprint.

Cite this