Sciweavers

4584 search results - page 915 / 917
» Sequential parameter optimization
Sort
View
ALT
2011
Springer
12 years 6 months ago
On the Expressive Power of Deep Architectures
Deep architectures are families of functions corresponding to deep circuits. Deep Learning algorithms are based on parametrizing such circuits and tuning their parameters so as to ...
Yoshua Bengio, Olivier Delalleau
CEC
2011
IEEE
12 years 6 months ago
Stochastic Natural Gradient Descent by estimation of empirical covariances
—Stochastic relaxation aims at finding the minimum of a fitness function by identifying a proper sequence of distributions, in a given model, that minimize the expected value o...
Luigi Malagò, Matteo Matteucci, Giovanni Pi...
IACR
2011
73views more  IACR 2011»
12 years 5 months ago
Secure Authentication from a Weak Key, Without Leaking Information
We study the problem of authentication based on a weak key in the information-theoretic setting. A key is weak if its min-entropy is an arbitrary small fraction of its bit length. ...
Niek J. Bouman, Serge Fehr
WSDM
2012
ACM
285views Data Mining» more  WSDM 2012»
12 years 1 months ago
Probabilistic models for personalizing web search
We present a new approach for personalizing Web search results to a specific user. Ranking functions for Web search engines are typically trained by machine learning algorithms u...
David Sontag, Kevyn Collins-Thompson, Paul N. Benn...
ISSTA
2012
ACM
11 years 8 months ago
A quantitative study of accuracy in system call-based malware detection
Over the last decade, there has been a significant increase in the number and sophistication of malware-related attacks and infections. Many detection techniques have been propos...
Davide Canali, Andrea Lanzi, Davide Balzarotti, Ch...