Sciweavers

1888 search results - page 200 / 378
» The Learning Power of Evolution
Sort
View
ICANN
2010
Springer
14 years 10 months ago
Multi-Dimensional Deep Memory Atari-Go Players for Parameter Exploring Policy Gradients
Abstract. Developing superior artificial board-game players is a widelystudied area of Artificial Intelligence. Among the most challenging games is the Asian game of Go, which, des...
Mandy Grüttner, Frank Sehnke, Tom Schaul, J&u...
JSW
2008
130views more  JSW 2008»
14 years 10 months ago
A Constraint-Driven Executable Model of Dynamic System Reconfiguration
Dynamic system reconfiguration techniques are presented that can enable the systematic evolution of software systems due to unanticipated changes in specification or requirements. ...
D'Arcy Walsh, Francis Bordeleau, Bran Selic
AIS
2000
Springer
14 years 10 months ago
Early-connectionism machines
: In this paper I put forward a reconstruction of the evolution of certain explanatory hypotheses on the neural basis of association and learning that are the premises of connectio...
Roberto Cordeschi
PIMRC
2010
IEEE
14 years 8 months ago
Statistical Learning-based Automated Healing: Application to mobility in 3G LTE networks
Abstract--Troubleshooting of wireless networks is a challenging network management task. We have developed, in a previous work, a new troubleshooting methodology, which we named St...
Moazzam Islam Tiwana, Berna Sayraç, Zwi Alt...
IDEAL
2009
Springer
14 years 8 months ago
Optimizing Data Transformations for Classification Tasks
Many classification algorithms use the concept of distance or similarity between patterns. Previous work has shown that it is advantageous to optimize general Euclidean distances (...
José María Valls, Ricardo Aler