On computational power and the order-chaos phase transition in reservoir computing
B Schrauwen, L Büsing… - Advances in neural …, 2008 - proceedings.neurips.cc
Randomly connected recurrent neural circuits have proven to be very powerful models for
online computations when a trained memoryless re adout function is appended. Such
Reservoir Computing (RC) systems are commonly used in two flavors: with analog or binary
(spiking) neurons in the recur rent circuits. Previous work showed a fundamental difference
between these two incarnations of the RC idea. The performance of a RC system built from
binary neuron s seems to depend strongly on the network connectivity structure. In network s …
online computations when a trained memoryless re adout function is appended. Such
Reservoir Computing (RC) systems are commonly used in two flavors: with analog or binary
(spiking) neurons in the recur rent circuits. Previous work showed a fundamental difference
between these two incarnations of the RC idea. The performance of a RC system built from
binary neuron s seems to depend strongly on the network connectivity structure. In network s …
[CITATION][C] On Computational Power and the Order-Chaos Phase Transition in Reservoir Computing
R Legenstein - 22nd Annual Conference on Neural …, 2008 - graz.elsevierpure.com
On Computational Power and the Order-Chaos Phase Transition in Reservoir Computing —
Graz University of Technology … On Computational Power and the Order-Chaos Phase
Transition in Reservoir Computing … 22nd Annual Conference on Neural Information
Processing Systems …
Graz University of Technology … On Computational Power and the Order-Chaos Phase
Transition in Reservoir Computing … 22nd Annual Conference on Neural Information
Processing Systems …
Showing the best results for this search. See all results