Sciweavers

748 search results - page 4 / 150
» A Reinforcement Learning Algorithm for Spiking Neural Networ...
Sort
View
GECCO
2005
Springer
155views Optimization» more  GECCO 2005»
14 years 3 days ago
Co-evolving recurrent neurons learn deep memory POMDPs
Recurrent neural networks are theoretically capable of learning complex temporal sequences, but training them through gradient-descent is too slow and unstable for practical use i...
Faustino J. Gomez, Jürgen Schmidhuber
IJCNN
2006
IEEE
14 years 19 days ago
Fast Modifications of the SpikeProp Algorithm
Abstract - In this paper we develop and analyze Spiking Neural Network (SNN) versions of Resilient Propagation (RProp) and QuickProp, both training methods used to speed up trainin...
Sam McKennoch, Dingding Liu, Linda G. Bushnell
ICANN
2007
Springer
14 years 22 days ago
SpikeStream: A Fast and Flexible Simulator of Spiking Neural Networks
SpikeStream is a new simulator of biologically structured spiking neural networks that can be used to edit, display and simulate up to 100,000 neurons. This simulator uses a combin...
David Gamez
ESOA
2006
13 years 10 months ago
Reinforcement Learning for Online Control of Evolutionary Algorithms
The research reported in this paper is concerned with assessing the usefulness of reinforcment learning (RL) for on-line calibration of parameters in evolutionary algorithms (EA). ...
A. E. Eiben, Mark Horvath, Wojtek Kowalczyk, Marti...