2027 search results - page 70 / 406 » Learning and Generalization with the Information Bottleneck |
TNN
2008
14 years 9 months ago
2008
This paper proposes an incremental multiple-object recognition and localization (IMORL) method. The objective of IMORL is to adaptively learn multiple interesting objects in an ima...
ATAL
2007
Springer
15 years 4 months ago
2007
Springer
This article deals with the problem of collaborative learning in a multi-agent system. Here each agent can update incrementally its beliefs B (the concept representation) so that ...
100
Voted
LAMAS
2005
Springer
15 years 3 months ago
2005
Springer
In this paper we report on using a relational state space in multi-agent reinforcement learning. There is growing evidence in the Reinforcement Learning research community that a r...
CIKM
2000
Springer
15 years 2 months ago
2000
Springer
We consider the problem of browsing the top ranked portion of the documents returned by an information retrieval system. We describe an interactive relevance feedback agent that a...
GECCO
2010
Springer
15 years 2 months ago
2010
Springer
Negative selection algorithms are immune-inspired classifiers that are trained on negative examples only. Classification is performed by generating detectors that match none of ...