Sciweavers

67 search results - page 11 / 14
» Towards Evolvable Analog Artificial Neural Networks Controll...
Sort
View
GECCO
2007
Springer
178views Optimization» more  GECCO 2007»
14 years 4 months ago
Nonlinear dynamics modelling for controller evolution
The problem of how to acquire a model of a physical robot, which is fit for evolution of controllers that can subsequently be used to control that robot, is considered in the con...
Julian Togelius, Renzo De Nardi, Hugo Gravato Marq...
ATAL
2005
Springer
14 years 3 months ago
PowerMatcher: multiagent control in the electricity infrastructure
Different driving forces push the electricity production towards decentralization. As a result, the current electricity infrastructure is expected to evolve into a network of netw...
J. K. Kok, C. J. Warmer, I. G. Kamphuis
ESANN
2006
13 years 11 months ago
Magnification control for batch neural gas
Neural gas (NG) constitutes a very robust clustering algorithm which can be derived as stochastic gradient descent from a cost function closely connected to the quantization error...
Barbara Hammer, Alexander Hasenfuss, Thomas Villma...
IJCNN
2006
IEEE
14 years 3 months ago
Patterns, Hypergraphs and Embodied General Intelligence
—It is proposed that the creation of Artificial General Intelligence (AGI) at the human level and ultimately beyond is a problem addressable via integrating computer science algo...
Ben Goertzel
GECCO
2007
Springer
182views Optimization» more  GECCO 2007»
14 years 1 months ago
Stochastic training of a biologically plausible spino-neuromuscular system model
A primary goal of evolutionary robotics is to create systems that are as robust and adaptive as the human body. Moving toward this goal often involves training control systems tha...
Stanley Phillips Gotshall, Terence Soule