Sciweavers

89 search results - page 8 / 18
» Margin-Based Active Learning for Structured Output Spaces
Sort
View
NN
2000
Springer
123views Neural Networks» more  NN 2000»
13 years 7 months ago
Local minima and plateaus in hierarchical structures of multilayer perceptrons
Local minima and plateaus pose a serious problem in learning of neural networks. We investigate the hierarchical geometric structure of the parameter space of three-layer perceptr...
Kenji Fukumizu, Shun-ichi Amari
HUMO
2007
Springer
14 years 1 months ago
Modeling Human Locomotion with Topologically Constrained Latent Variable Models
Abstract. Learned, activity-specific motion models are useful for human pose and motion estimation. Nevertheless, while the use of activityspecific models simplifies monocular t...
Raquel Urtasun, David J. Fleet, Neil D. Lawrence
ACSAC
2008
IEEE
14 years 2 months ago
Structuring for Strategic Cyber Defense: A Cyber Manhattan Project Blueprint
In February 2002, more than 50 leaders in the information assurance field warned the President of the United States of a national strategic vulnerability in the country’s inform...
O. Sami Saydjari
CVPR
2012
IEEE
11 years 10 months ago
Max-margin early event detectors
The need for early detection of temporal events from sequential data arises in a wide spectrum of applications ranging from human-robot interaction to video security. While tempor...
Minh Hoai Nguyen, Fernando De la Torre
ICML
2008
IEEE
14 years 8 months ago
Modeling interleaved hidden processes
Hidden Markov models assume that observations in time series data stem from some hidden process that can be compactly represented as a Markov chain. We generalize this model by as...
Niels Landwehr