Sciweavers

225 search results - page 20 / 45
» ADANN: automatic design of artificial neural networks
Sort
View
CEC
2007
IEEE
14 years 4 months ago
Combine and compare evolutionary robotics and reinforcement Learning as methods of designing autonomous robots
—The purpose of this paper is to present a comparison between two methods of building adaptive controllers for robots. In spite of the wide range of techniques which are used for...
Sergiu Goschin, Eduard Franti, Monica Dascalu, San...
CASES
2006
ACM
14 years 4 months ago
Automatic performance model construction for the fast software exploration of new hardware designs
Developing an optimizing compiler for a newly proposed architecture is extremely difficult when there is only a simulator of the machine available. Designing such a compiler requ...
John Cavazos, Christophe Dubach, Felix V. Agakov, ...
ECAL
2005
Springer
14 years 4 months ago
(Co)Evolution of (De)Centralized Neural Control for a Gravitationally Driven Machine
Using decentralized control structures for robot control can offer a lot of advantages, such as less complexity, better fault tolerance and more flexibility. In this paper the ev...
Steffen Wischmann, Martin Hülse, Frank Pasema...
IJCNN
2008
IEEE
14 years 4 months ago
A comparison of fuzzy ARTMAP and Gaussian ARTMAP neural networks for incremental learning
Abstract— Automatic pattern classifiers that allow for incremental learning can adapt internal class models efficiently in response to new information, without having to retrai...
Eric Granger, Jean-François Connolly, Rober...
CEC
2008
IEEE
14 years 4 months ago
Automatic model type selection with heterogeneous evolution: An application to RF circuit block modeling
— Many complex, real world phenomena are difficult to study directly using controlled experiments. Instead, the use of computer simulations has become commonplace as a cost effe...
Dirk Gorissen, Luciano De Tommasi, Jeroen Croon, T...