Sciweavers

1997 search results - page 214 / 400
» On the convergence of Hill's method
Sort
View
ICIP
2010
IEEE
14 years 10 months ago
Snakules: Snakes that seek spicules on mammography
We present a new method called "snakules" for the annotation of spicules on mammography. Snakules employs parametric open-ended snakes that are deployed in a region arou...
Gautam S. Muralidhar, Alan C. Bovik, Mia K. Markey
CDC
2010
IEEE
145views Control Systems» more  CDC 2010»
14 years 8 months ago
Construction of Lyapunov functions for piecewise-deterministic Markov processes
The purpose of this contribution is twofold: 1) to present for the first time a Lyapunov function that proves exponential ergodicity of a process studied by the authors in [1], whe...
Alexandre R. Mesquita, João Pedro Hespanha
SAC
2011
ACM
14 years 8 months ago
A quasi-Newton acceleration for high-dimensional optimization algorithms
Abstract In many statistical problems, maximum likelihood estimation by an EM or MM algorithm suffers from excruciatingly slow convergence. This tendency limits the application of ...
Hua Zhou, David Alexander, Kenneth Lange
JMLR
2010
132views more  JMLR 2010»
14 years 8 months ago
Learning Gradients: Predictive Models that Infer Geometry and Statistical Dependence
The problems of dimension reduction and inference of statistical dependence are addressed by the modeling framework of learning gradients. The models we propose hold for Euclidean...
Qiang Wu, Justin Guinney, Mauro Maggioni, Sayan Mu...
JMLR
2010
108views more  JMLR 2010»
14 years 8 months ago
Sufficient Dimension Reduction via Squared-loss Mutual Information Estimation
The goal of sufficient dimension reduction in supervised learning is to find the lowdimensional subspace of input features that is `sufficient' for predicting output values. ...
Taiji Suzuki, Masashi Sugiyama