Sciweavers

171 search results - page 31 / 35
» Viewpoint Selection for Human Actions
Sort
View
73
Voted
SMC
2007
IEEE
102views Control Systems» more  SMC 2007»
15 years 3 months ago
An improved immune Q-learning algorithm
—Reinforcement learning is a framework in which an agent can learn behavior without knowledge on a task or an environment by exploration and exploitation. Striking a balance betw...
Zhengqiao Ji, Q. M. Jonathan Wu, Maher A. Sid-Ahme...
ICDM
2010
IEEE
208views Data Mining» more  ICDM 2010»
14 years 7 months ago
Bonsai: Growing Interesting Small Trees
Graphs are increasingly used to model a variety of loosely structured data such as biological or social networks and entityrelationships. Given this profusion of large-scale graph ...
Stephan Seufert, Srikanta J. Bedathur, Juliá...
JMLR
2012
12 years 12 months ago
Maximum Margin Temporal Clustering
Temporal Clustering (TC) refers to the factorization of multiple time series into a set of non-overlapping segments that belong to k temporal clusters. Existing methods based on e...
Minh Hoai Nguyen, Fernando De la Torre
CHI
2001
ACM
15 years 10 months ago
Ignoring perfect knowledge in-the-world for imperfect knowledge in-the-head
Constraints and dependencies among the elements of embodied cognition form patterns or microstrategies of interactive behavior. Hard constraints determine which microstrategies ar...
Wayne D. Gray, Wai-Tat Fu
CCECE
2006
IEEE
15 years 3 months ago
A Dynamic Associative E-Learning Model based on a Spreading Activation Network
Presenting information to an e-learning environment is a challenge, mostly, because ofthe hypertextlhypermedia nature and the richness ofthe context and information provides. This...
Phongchai Nilas, Nilamit Nilas, Somsak Mitatha