Echo State Networks

Exploiting Multiple Timescales in Hierarchical Echo State Networks

Echo state networks (ESNs) are a powerful form of reservoir computing that only require training of linear output weights while the internal reservoir is formed of fixed randomly connected neurons. With a correctly scaled connectivity matrix, the …

Upcoming Papers

It was nice early Christmas present that we heard that two of our recent submissions had been accepted. The first was invited article in Frontiers in Applied Mathematics and Statistics where we have been looking at hierarchical (or deep) echo state networks and how we can tune them to exhibit multiple timescales.