Sciweavers

2217 search results - page 126 / 444
» Learning from Collective Behavior
Sort
View
ATAL
2010
Springer
13 years 10 months ago
Combining manual feedback with subsequent MDP reward signals for reinforcement learning
As learning agents move from research labs to the real world, it is increasingly important that human users, including those without programming skills, be able to teach agents de...
W. Bradley Knox, Peter Stone
CSL
2010
Springer
13 years 9 months ago
Active learning and semi-supervised learning for speech recognition: A unified framework using the global entropy reduction maxi
We propose a unified global entropy reduction maximization (GERM) framework for active learning and semi-supervised learning for speech recognition. Active learning aims to select...
Dong Yu, Balakrishnan Varadarajan, Li Deng, Alex A...
HICSS
2008
IEEE
147views Biometrics» more  HICSS 2008»
14 years 3 months ago
Can Peer-to-Peer Networks Facilitate Information Sharing in Collaborative Learning?
Many peer-to-peer (P2P) networks have been widely used for file sharing. A peer acts both as a content provider and a consumer, and is granted autonomy to decide what content, wit...
Fu-ren Lin, Sheng-cheng Lin, Ying-fen Wang
ICCSA
2009
Springer
14 years 4 months ago
Learning and Predicting Key Web Navigation Patterns Using Bayesian Models
Abstract. The accurate prediction of Web navigation patterns has immense commercial value as the Web evolves into a primary medium for marketing and sales for many businesses. Ofte...
Malik Tahir Hassan, Khurum Nazir Junejo, Asim Kari...
TOG
2002
167views more  TOG 2002»
13 years 8 months ago
Interactive control of avatars animated with human motion data
Real-time control of three-dimensional avatars is an important problem in the context of computer games and virtual environments. Avatar animation and control is difficult, howeve...
Jehee Lee, Jinxiang Chai, Paul S. A. Reitsma, Jess...