Sciweavers

3625 search results - page 233 / 725
» On choosing
Sort
View
ML
1998
ACM
136views Machine Learning» more  ML 1998»
15 years 7 months ago
Co-Evolution in the Successful Learning of Backgammon Strategy
Following Tesauro’s work on TD-Gammon, we used a 4000 parameter feed-forward neural network to develop a competitive backgammon evaluation function. Play proceeds by a roll of t...
Jordan B. Pollack, Alan D. Blair
NN
2002
Springer
224views Neural Networks» more  NN 2002»
15 years 7 months ago
Optimal design of regularization term and regularization parameter by subspace information criterion
The problem of designing the regularization term and regularization parameter for linear regression models is discussed. Previously, we derived an approximation to the generalizat...
Masashi Sugiyama, Hidemitsu Ogawa
RAS
2002
92views more  RAS 2002»
15 years 7 months ago
Information Sampling for vision-based robot navigation
This paper proposes a statistical, non-feature based, attention mechanism for a mobile robot, termed Information Sampling. The selected data may be a single pixel or a number scat...
Niall Winters, José Santos-Victor
RE
2002
Springer
15 years 7 months ago
Requirements Engineering in the Health Care Domain
There are many different approaches to elicit requirements each having its strengths and weaknesses. Hence, some approaches may be ore suitable to one domain then another. Moreove...
Luiz Marcio Cysneiros
TEC
2002
163views more  TEC 2002»
15 years 7 months ago
Ants can solve constraint satisfaction problems
In this paper, we describe a new incomplete approach for solving constraint satisfaction problems (CSPs) based on the ant colony optimization (ACO) metaheuristic. The idea is to us...
Christine Solnon