Publication
Gradient estimates of return
Publications associées (32)
An optimal error nonlinearity for robust adaptation against impulsive noise
The least-mean squares algorithm is non-robust against impulsive noise. Incorporating an error nonlinearity into the update equation is one useful way to mitigate the effects of impulsive noise. This work develops an adaptive structure that parametrically ...
IEEE2013Estimation of displacement derivatives in digital holographic interferometry using a two-dimensional space-frequency distribution
Pramod Rastogi, Sai Siva Gorthi
The paper introduces a two-dimensional space-frequency distribution based method to directly obtain the unwrapped estimate of the phase derivative which corresponds to strain in digital holographic interferometry. In the proposed method, a two-dimensional ...
Optical Society of America2010Intégration énergétique d’un procédé agroalimentaire à l’aide de la plateforme internet PinchLight
Résumé : Les procédés agroalimentaires sont des procédés industriels consommateurs de grandes quantités d’énergie, aussi bien de refroidissement que de chauffage. Il est donc intéressant d’optimiser cette consommation. L’analyse pinch, méthode systématique ...
2010Diffusion adaptive networks with changing topologies
daptive networks (AN) have been recently proposed to address distributed estimation problems [1]–[4]. Here we extend prior work to changing topologies and data-normalized algorithms. The resulting framework may also treat signals with general distributions ...
IEEE2008Crystallisation of calcium hydroxide in early age model and ordinary cementitious systems
Karen Scrivener, Emmanuel Gallucci
The distribution and morphology of CH particles in various cementitious systems was investigated to determine which parameters influence their nucleation and growth. Morphological image analysis of SEM-BSE images of polished cross-sections was used to meas ...
2007A Discriminative Approach for the Retrieval of Images from Text Queries
Samy Bengio, David Grangier, Florent Monay Michaud
This work proposes a new approach to the retrieval of images from text queries. Contrasting with previous work, this method relies on a discriminative approach: the parameters are selected in order to minimize a loss related to the ranking performance of t ...
IDIAP2006A Discriminative Approach for the Retrieval of Images from Text Queries
Samy Bengio, David Grangier, Florent Monay Michaud
This work proposes a new approach to the retrieval of images from text queries. Contrasting with previous work, this method relies on a discriminative model: the parameters are selected in order to minimize a loss related to the ranking performance of the ...
2006Analytic Determination of Scaling Parameters
Rüdiger Urbanke, Abdelaziz Amraoui, Andrea Montanari
We show that the finite-length scaling parameters for irregular LDPC codes when used over the binary erasure channel can be computed without resorting to ``covariance evolution''. We provide simple expressions that can be evaluated using solely the degree ...
2006Probabilistic Tagging of Unstructured Genealogical Records
In this paper we present a method of parsing unstructured textual records briefly describing a person and their direct relatives. The string `Stephanus, brother of Johannes Magnin, from Saillon' is a typical example of a record. We wish to annotate every t ...
IDIAP2005Mixture models for multivariate extremes
This thesis is a contribution to multivariate extreme value statistics. The tail of a multivariate distribution function is characterized by its spectral distribution, for which we propose a new semi-parametric model based on mixtures of Dirichlet distribu ...
EPFL2004