Sciweavers

23 search results - page 3 / 5
» Evolving neural networks for fractured domains
Sort
View
GECCO
2010
Springer
173views Optimization» more  GECCO 2010»
13 years 10 months ago
Evolving the placement and density of neurons in the hyperneat substrate
The Hypercube-based NeuroEvolution of Augmenting Topologies (HyperNEAT) approach demonstrated that the pattern of weights across the connectivity of an artificial neural network ...
Sebastian Risi, Joel Lehman, Kenneth O. Stanley
GECCO
2007
Springer
172views Optimization» more  GECCO 2007»
13 years 12 months ago
Acquiring evolvability through adaptive representations
Adaptive representations allow evolution to explore the space of phenotypes by choosing the most suitable set of genotypic parameters. Although such an approach is believed to be ...
Joseph Reisinger, Risto Miikkulainen
GECCO
2007
Springer
182views Optimization» more  GECCO 2007»
13 years 12 months ago
Generating large-scale neural networks through discovering geometric regularities
Connectivity patterns in biological brains exhibit many repeating motifs. This repetition mirrors inherent geometric regularities in the physical world. For example, stimuli that ...
Jason Gauci, Kenneth O. Stanley
SEAL
1998
Springer
13 years 10 months ago
Co-evolution, Determinism and Robustness
Abstract. Robustness has long been recognised as a critical issue for coevolutionary learning. It has been achieved in a number of cases, though usually in domains which involve so...
Alan D. Blair, Elizabeth Sklar, Pablo Funes
GECCO
2006
Springer
208views Optimization» more  GECCO 2006»
13 years 9 months ago
Comparing evolutionary and temporal difference methods in a reinforcement learning domain
Both genetic algorithms (GAs) and temporal difference (TD) methods have proven effective at solving reinforcement learning (RL) problems. However, since few rigorous empirical com...
Matthew E. Taylor, Shimon Whiteson, Peter Stone