1258 search results - page 132 / 252 » Architecture-driven Problem Decomposition |
NPL
2006
13 years 9 months ago
2006
Hierarchical Incremental Class Learning (HICL) is a new task decomposition method that addresses the pattern classification problem. HICL is proven to be a good classifier but clos...
CVPR
2005
IEEE
14 years 11 months ago
2005
IEEE
Matrix factorization has many applications in computer vision. Singular Value Decomposition (SVD) is the standard algorithm for factorization. When there are outliers and missing ...
ICML
2002
IEEE
14 years 9 months ago
2002
IEEE
Two notions of optimality have been explored in previous work on hierarchical reinforcement learning (HRL): hierarchical optimality, or the optimal policy in the space defined by ...
FOCS
2004
IEEE
14 years 23 days ago
2004
IEEE
We study the maximum edge-disjoint paths problem in undirected planar graphs: given a graph G and node pairs (demands) s1t1, s2t2, . . ., sktk, the goal is to maximize the number ...
IJCAI
2003
13 years 10 months ago
2003
With the growing use of distributed information networks, there is an increasing need for algorithmic and system solutions for data-driven knowledge acquisition using distributed,...