Sciweavers

704 search results - page 7 / 141
» Improved Learning of AC0 Functions
Sort
View
CVPR
2008
IEEE
13 years 9 months ago
Improving local learning for object categorization by exploring the effects of ranking
Local learning for classification is useful in dealing with various vision problems. One key factor for such approaches to be effective is to find good neighbors for the learning ...
Tien-Lung Chang, Tyng-Luh Liu, Jen-Hui Chuang
GECCO
2004
Springer
122views Optimization» more  GECCO 2004»
14 years 27 days ago
Gradient-Based Learning Updates Improve XCS Performance in Multistep Problems
This paper introduces a gradient-based reward prediction update mechanism to the XCS classifier system as applied in neuralnetwork type learning and function approximation mechani...
Martin V. Butz, David E. Goldberg, Pier Luca Lanzi
SIGIR
2011
ACM
12 years 10 months ago
A boosting approach to improving pseudo-relevance feedback
Pseudo-relevance feedback has proven effective for improving the average retrieval performance. Unfortunately, many experiments have shown that although pseudo-relevance feedback...
Yuanhua Lv, ChengXiang Zhai, Wan Chen
GECCO
2006
Springer
196views Optimization» more  GECCO 2006»
13 years 11 months ago
An anticipatory approach to improve XCSF
XCSF is a novel version of learning classifier systems (LCS) which extends the typical concept of LCS by introducing computable classifier prediction. In XCSF Classifier predictio...
Amin Nikanjam, Adel Torkaman Rahmani
ESANN
2001
13 years 9 months ago
Learning fault-tolerance in Radial Basis Function Networks
This paper describes a method of supervised learning based on forward selection branching. This method improves fault tolerance by means of combining information related to general...
Xavier Parra, Andreu Català