Sciweavers

370 search results - page 33 / 74
» Evolving neural network ensembles for control problems
Sort
View
ICANNGA
2009
Springer
203views Algorithms» more  ICANNGA 2009»
14 years 2 months ago
NEAT in HyperNEAT Substituted with Genetic Programming
In this paper we present application of genetic programming (GP) [1] to evolution of indirect encoding of neural network weights. We compare usage of original HyperNEAT algorithm w...
Zdenek Buk, Jan Koutník, Miroslav Snorek
TSMC
1998
135views more  TSMC 1998»
13 years 7 months ago
Universal stabilization using control Lyapunov functions, adaptive derivative feedback, and neural network approximators
— In this paper, the problem of stabilization of unknown nonlinear dynamical systems is considered. An adaptive feedback law is constructed that is based on the switching adaptiv...
Elias B. Kosmatopoulos
ROBOCUP
2007
Springer
96views Robotics» more  ROBOCUP 2007»
14 years 1 months ago
A Neural Network-Based Approach to Robot Motion Control
The joint controllers used in robots like the Sony Aibo are designed for the task of moving the joints of the robot to a given position. However, they are not well suited to the pr...
Uli Grasemann, Daniel Stronger, Peter Stone
GECCO
2007
Springer
182views Optimization» more  GECCO 2007»
14 years 1 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
GECCO
2010
Springer
173views Optimization» more  GECCO 2010»
13 years 11 months ago
The baldwin effect in developing neural networks
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...
Keith L. Downing