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 language | English |
---|---|
Title of host publication | ESANN'2009 Proceedings: 17th European Symposium on Artificial Networks: Advances in Computational Intelligence and Learning, Bruges, Belgium, 22-24 April 2009 |
Publisher | d-side |
Pages | 227-232 |
Number of pages | 6 |
ISBN (Print) | 9782930307091 |
Publication status | Published - 2009 |
Event | European Symposium on Artificial Neural Networks - Duration: 22 Apr 2009 → … |
Conference
Conference | European Symposium on Artificial Neural Networks |
---|---|
Period | 22/04/09 → … |
Keywords
- neural networks (computer science)
- reservoir computing