Sciweavers

1931 search results - page 239 / 387
» Why we blog
Sort
View
JMLR
2010
151views more  JMLR 2010»
15 years 1 months ago
Understanding the difficulty of training deep feedforward neural networks
Whereas before 2006 it appears that deep multilayer neural networks were not successfully trained, since then several algorithms have been shown to successfully train them, with e...
Xavier Glorot, Yoshua Bengio
CORR
2011
Springer
168views Education» more  CORR 2011»
15 years 1 months ago
Submodular meets Spectral: Greedy Algorithms for Subset Selection, Sparse Approximation and Dictionary Selection
We study the problem of selecting a subset of k random variables from a large set, in order to obtain the best linear prediction of another variable of interest. This problem can ...
Abhimanyu Das, David Kempe
IACR
2011
85views more  IACR 2011»
14 years 6 months ago
Some Instant- and Practical-Time Related-Key Attacks on KTANTAN32/48/64
The hardware-attractive block cipher family KTANTAN was studied by Bogdanov and Rechberger who identified flaws in the key schedule and gave a meet-in-the-middle attack. We revis...
Martin Ågren
CVPR
2004
IEEE
16 years 9 months ago
Spherical Harmonics vs. Haar Wavelets: Basis for Recovering Illumination from Cast Shadows
The problem of estimating an illumination distribution from images is called inverse lighting. For inverse lighting, three approaches have been developed based on specular reflect...
Takahiro Okabe, Imari Sato, Yoichi Sato
ICCV
2005
IEEE
16 years 9 months ago
A Multi-Scale Hybrid Linear Model for Lossy Image Representation
This paper introduces a simple and efficient representation for natural images. We partition an image into blocks and treat the blocks as vectors in a high-dimensional space. We t...
Wei Hong, John Wright, Kun Huang, Yi Ma