Sciweavers

1888 search results - page 268 / 378
» The Learning Power of Evolution
Sort
View
CVPR
2007
IEEE
16 years 16 hour ago
Eigenboosting: Combining Discriminative and Generative Information
A major shortcoming of discriminative recognition and detection methods is their noise sensitivity, both during training and recognition. This may lead to very sensitive and britt...
Helmut Grabner, Peter M. Roth, Horst Bischof
CVPR
2008
IEEE
16 years 15 hour ago
Joint data alignment up to (lossy) transformations
Joint data alignment is often regarded as a data simplification process. This idea is powerful and general, but raises two delicate issues. First, one must make sure that the usef...
Andrea Vedaldi, Gregorio Guidi, Stefano Soatto
KDD
2005
ACM
109views Data Mining» more  KDD 2005»
15 years 10 months ago
Overcoming Incomplete User Models in Recommendation Systems Via an Ontology
Abstract. To make accurate recommendations, recommendation systems currently require more data about a customer than is usually available. We conjecture that the weaknesses are due...
Vincent Schickel-Zuber, Boi Faltings
OSDI
2008
ACM
15 years 10 months ago
Binary Translation Using Peephole Superoptimizers
We present a new scheme for performing binary translation that produces code comparable to or better than existing binary translators with much less engineering effort. Instead of...
Sorav Bansal, Alex Aiken
CISS
2008
IEEE
15 years 4 months ago
Achievable rates and training optimization for fading relay channels with memory
—In this paper, transmission over time-selective, flat fading relay channels is studied. It is assumed that channel fading coefficients are not known a priori. Transmission tak...
Sami Akin, Mustafa Cenk Gursoy