Sciweavers

10054 search results - page 163 / 2011
» On the Complexity of Function Learning
Sort
View
TAL
2010
Springer
14 years 10 months ago
Passage Retrieval in Log Files: An Approach Based on Query Enrichment
Abstract. The question answering systems are considered the next generation of search engines. This paper focuses on the first step of this process, which is to search for relevant...
Hassan Saneifar, Stéphane Bonniol, Anne Lau...
86
Voted
ESANN
2001
15 years 2 months ago
Optimal transfer function neural networks
Neural networks use neurons of the same type in each layer but such architecture cannot lead to data models of optimal complexity and accuracy. Networks with architectures (number ...
Norbert Jankowski, Wlodzislaw Duch
LATINCRYPT
2010
14 years 11 months ago
Message Recovery and Pseudo-preimage Attacks on the Compression Function of Hamsi-256
Hamsi is one of the second round candidates of the SHA-3 competition. In this study, we present non-random differential properties for the compression function of the hash functio...
Çagdas Çalik, Meltem Sönmez Tur...
COLT
1995
Springer
15 years 4 months ago
Regression NSS: An Alternative to Cross Validation
The Noise Sensitivity Signature (NSS), originally introduced by Grossman and Lapedes (1993), was proposed as an alternative to cross validation for selecting network complexity. I...
Michael P. Perrone, Brian S. Blais
ICML
2008
IEEE
16 years 1 months ago
A worst-case comparison between temporal difference and residual gradient with linear function approximation
Residual gradient (RG) was proposed as an alternative to TD(0) for policy evaluation when function approximation is used, but there exists little formal analysis comparing them ex...
Lihong Li