Sciweavers

973 search results - page 83 / 195
» New Bounds on Crossing Numbers
Sort
View
PAKDD
2004
ACM
131views Data Mining» more  PAKDD 2004»
15 years 5 months ago
A Tree-Based Approach to the Discovery of Diagnostic Biomarkers for Ovarian Cancer
Computational diagnosis of cancer is a classification problem, and it has two special requirements on a learning algorithm: perfect accuracy and small number of features used in t...
Jinyan Li, Kotagiri Ramamohanarao
CIDR
2011
234views Algorithms» more  CIDR 2011»
14 years 3 months ago
SWissBox: An Architecture for Data Processing Appliances
Database appliances offer fully integrated hardware, storage, operating system, database, and related software in a single package. Database appliances have a relatively long hist...
Gustavo Alonso, Donald Kossmann, Timothy Roscoe
COLT
2006
Springer
15 years 3 months ago
Online Learning Meets Optimization in the Dual
We describe a novel framework for the design and analysis of online learning algorithms based on the notion of duality in constrained optimization. We cast a sub-family of universa...
Shai Shalev-Shwartz, Yoram Singer
DCG
2007
91views more  DCG 2007»
14 years 12 months ago
Which n-Venn Diagrams Can Be Drawn with Convex k-Gons?
We establish a new lower bound for the number of sides required for the component curves of simple Venn diagrams made from polygons. Specifically, for any n-Venn diagram of conve...
Jeremy Carroll, Frank Ruskey, Mark Weston
DAGM
2004
Springer
15 years 3 months ago
MinOver Revisited for Incremental Support-Vector-Classification
The well-known and very simple MinOver algorithm is reformulated for incremental support vector classification with and without kernels. A modified proof for its O(t-1/2 ) converge...
Thomas Martinetz