Sciweavers

1455 search results - page 37 / 291
» Exploiting Myopic Learning
Sort
View
ICML
2003
IEEE
16 years 3 months ago
The Use of the Ambiguity Decomposition in Neural Network Ensemble Learning Methods
We analyze the formal grounding behind Negative Correlation (NC) Learning, an ensemble learning technique developed in the evolutionary computation literature. We show that by rem...
Gavin Brown, Jeremy L. Wyatt
108
Voted
ICTAI
2009
IEEE
15 years 9 months ago
Learning for Dynamic Assignments Reordering
In this paper a new learning scheme for SAT is proposed. The originality of our approach arises from its ability to achieve clause learning even if no conflict occurs. This clear...
Saïd Jabbour
134
Voted
ICALT
2009
IEEE
15 years 5 months ago
On-demand Construction of Personalized Learning Experiences Using Semantic Web and Web 2.0 Techniques
Nowadays, the Semantic Web technologies are exploited also in the e-learning domain in order to provide personalized and adaptive learning experiences, semantic annotation of lear...
Nicola Capuano, Matteo Gaeta, Francesco Orciuoli, ...
146
Voted
GECCO
2008
Springer
145views Optimization» more  GECCO 2008»
15 years 3 months ago
Towards incremental social learning in optimization and multiagent systems
Social learning is a mechanism that allows individuals to acquire knowledge from others without incurring the costs of acquiring it individually. Individuals that learn socially c...
Marco Antonio Montes de Oca, Thomas Stützle
129
Voted
NN
2002
Springer
113views Neural Networks» more  NN 2002»
15 years 2 months ago
Control of exploitation-exploration meta-parameter in reinforcement learning
In reinforcement learning (RL), the duality between exploitation and exploration has long been an important issue. This paper presents a new method that controls the balance betwe...
Shin Ishii, Wako Yoshida, Junichiro Yoshimoto