no code implementations • 19 May 2022 • Norbert Michael Mayer, Oliver Obst
This connection between fractal dimension and network connectivity is an interesting new direction for recurrent neural network initialization and reservoir computing.
no code implementations • 12 Jun 2016 • Norbert Michael Mayer
The paper investigates a new type of truly critical echo state networks where individual transfer functions for every neuron can be modified to anticipate the expected next input.
no code implementations • 22 Jan 2016 • Norbert Michael Mayer, Ying-Hao Yu
We report about probabilistic likelihood estimates that are performed on time series using an echo state network with orthogonal recurrent connectivity.
no code implementations • 25 Nov 2014 • Norbert Michael Mayer
Recurrent networks with transfer functions that fulfill the Lipschitz continuity with K=1 may be echo state networks if certain limitations on the recurrent connectivity are applied.
no code implementations • 25 Apr 2014 • Norbert Michael Mayer
Usually, reservoir computing shows an exponential memory decay.