Sciweavers

1922 search results - page 310 / 385
» ie 2007
Sort
View
NIPS
2003
14 years 11 months ago
Boosting versus Covering
We investigate improvements of AdaBoost that can exploit the fact that the weak hypotheses are one-sided, i.e. either all its positive (or negative) predictions are correct. In pa...
Kohei Hatano, Manfred K. Warmuth
ICISC
1998
110views Cryptology» more  ICISC 1998»
14 years 11 months ago
The nonhomomorphicity of S-boxes
Abstract. In this paper, we introduce the concept of kth-order nonhomomorphicity of mappings or S-boxes as an alternative indicator that forecasts nonlinearity characteristics of a...
Yuliang Zheng, Xian-Mo Zhang
NIPS
1998
14 years 11 months ago
Modeling Surround Suppression in V1 Neurons with a Statistically Derived Normalization Model
We examine the statistics of natural monochromatic images decomposed using a multi-scale wavelet basis. Although the coefficients of this representation are nearly decorrelated, t...
Eero P. Simoncelli, Odelia Schwartz
NIPS
2000
14 years 11 months ago
The Use of MDL to Select among Computational Models of Cognition
How should we decide among competing explanations of a cognitive process given limited observations? The problem of model selection is at the heart of progress in cognitive scienc...
In Jae Myung, Mark A. Pitt, Shaobo Zhang, Vijay Ba...
NIPS
1997
14 years 11 months ago
Relative Loss Bounds for Multidimensional Regression Problems
We study on-line generalized linear regression with multidimensional outputs, i.e., neural networks with multiple output nodes but no hidden nodes. We allow at the final layer tra...
Jyrki Kivinen, Manfred K. Warmuth