47 search results - page 8 / 10 » An Accelerating Learning Algorithm for Block-Diagonal Recurr... |
CEC
2008
IEEE
14 years 2 months ago
2008
IEEE
— We evolve a neural network controller for a boat that learns to maintain a given bearing and range with respect to a moving target in the Lagoon 3D game environment. Simulating...
IJIT
2004
13 years 9 months ago
2004
Since the presentation of the backpropagation algorithm, a vast variety of improvements of the technique for training a feed forward neural networks have been proposed. This articl...
GECCO
2008
Springer
13 years 8 months ago
2008
Springer
A possible alternative to fine topology tuning for Neural Network (NN) optimization is to use Echo State Networks (ESNs), recurrent NNs built upon a large reservoir of sparsely r...
GECCO
2010
Springer
13 years 11 months ago
2010
Springer
The Baldwin Effect is a very plausible, but unproven, biological theory concerning the power of learning to accelerate evolution. Simple computational models in the 1980’s gave...
AR
2007
13 years 7 months ago
2007
—Reinforcement learning is the scheme for unsupervised learning in which robots are expected to acquire behavior skills through self-explorations based on reward signals. There a...