Sciweavers

13 search results - page 1 / 3
» On Computational Power and the Order-Chaos Phase Transition ...
Sort
View
NIPS
2008
13 years 6 months ago
On Computational Power and the Order-Chaos Phase Transition in Reservoir Computing
Randomly connected recurrent neural circuits have proven to be very powerful models for online computations when a trained memoryless readout function is appended. Such Reservoir ...
Benjamin Schrauwen, Lars Buesing, Robert A. Legens...
NECO
2010
147views more  NECO 2010»
13 years 3 months ago
Connectivity, Dynamics, and Memory in Reservoir Computing with Binary and Analog Neurons
Abstract: Reservoir Computing (RC) systems are powerful models for online computations on input sequences. They consist of a memoryless readout neuron which is trained on top of a ...
Lars Büsing, Benjamin Schrauwen, Robert A. Le...
IMR
2004
Springer
13 years 10 months ago
3D Hybrid Mesh Generation for Reservoir Flow Simulation
A great challenge for flow simulators of new generation is to gain more accuracy at well proximity within complex geological structures. For this purpose, a new approach based on...
N. Flandrin, Houman Borouchaki, Chakib Bennis
IJCNN
2006
IEEE
13 years 11 months ago
Echo State Networks for Determining Harmonic Contributions from Nonlinear Loads
—This paper investigates the application of a new kind of recurrent neural network called Echo State Networks (ESNs) for the problem of measuring the actual amount of harmonic cu...
Joy Mazumdar, Ganesh K. Venayagamoorthy, Ronald G....
FOCS
2007
IEEE
13 years 11 months ago
Mixing Time Power Laws at Criticality
We study the mixing time of some Markov Chains converging to critical physical models. These models are indexed by a parameter β and there exists some critical value βc where th...
Yun Long, Asaf Nachmias, Yuval Peres