Sciweavers

74 search results - page 15 / 15
» A New Approach to Knowledge-Based Design of Recurrent Neural...
Sort
View
GECCO
2007
Springer
178views Optimization» more  GECCO 2007»
13 years 11 months ago
Coevolution of intelligent agents using cartesian genetic programming
A coevolutionary competitive learning environment for two antagonistic agents is presented. The agents are controlled by a new kind of computational network based on a compartment...
Gul Muhammad Khan, Julian Francis Miller, David M....
COLT
2006
Springer
13 years 9 months ago
Efficient Learning Algorithms Yield Circuit Lower Bounds
We describe a new approach for understanding the difficulty of designing efficient learning algorithms. We prove that the existence of an efficient learning algorithm for a circui...
Lance Fortnow, Adam R. Klivans
GECCO
2007
Springer
177views Optimization» more  GECCO 2007»
13 years 11 months ago
Evolving virtual creatures revisited
Thirteen years have passed since Karl Sims published his work on evolving virtual creatures. Since then, several novel approaches to neural network evolution and genetic algorithm...
Peter Krcah
GECCO
2010
Springer
184views Optimization» more  GECCO 2010»
13 years 10 months ago
Transfer learning through indirect encoding
An important goal for the generative and developmental systems (GDS) community is to show that GDS approaches can compete with more mainstream approaches in machine learning (ML)....
Phillip Verbancsics, Kenneth O. Stanley