Concept

Fonction softmax

Publications associées (70)

Graph Chatbot

Chattez avec Graph Search

Posez n’importe quelle question sur les cours, conférences, exercices, recherches, actualités, etc. de l’EPFL ou essayez les exemples de questions ci-dessous.

AVERTISSEMENT : Le chatbot Graph n'est pas programmé pour fournir des réponses explicites ou catégoriques à vos questions. Il transforme plutôt vos questions en demandes API qui sont distribuées aux différents services informatiques officiellement administrés par l'EPFL. Son but est uniquement de collecter et de recommander des références pertinentes à des contenus que vous pouvez explorer pour vous aider à répondre à vos questions.

Connectez-vous pour utiliser Chat avec Graph Search

Compressive sensing meets game theory

Volkan Cevher, Sina Jafarpour

We introduce the Multiplicative Update Selector and Estimator (MUSE) algorithm for sparse approximation in under-determined linear regression problems. Given ƒ = Φα* + μ, the MUSE provably and efficiently finds a k-sparse vector α̂ such that ∥Φα̂ − ƒ∥∞ ≤ ∥ ...

IEEE2011

MLP Based Hierarchical System for Task Adaptation in ASR

Hervé Bourlard, Joel Praveen Pinto

We investigate a multilayer perceptron (MLP) based hierarchical approach for task adaptation in automatic speech recognition. The system consists of two MLP classifiers in tandem. A well-trained MLP available off-the-shelf is used at the first stage of the ...

2009

Parasites lead to evolution of robustness against gene loss in host signaling networks

Marcel Salathé

Many biological networks can maintain their function against single gene loss. However, the evolutionary mechanisms responsible for such robustness remain unclear. Here, we demonstrate that antagonistic host-parasite interactions can act as a selective pre ...

Nature / European Molecular Biology Organization2008

Electron heat transport studies

Yann Camenen

Electron transport in fusion plasmas is intensively studied in coordinated experiments and great progress in physics understanding has been achieved during the past years. A threshold in normalized gradient explains most of the observations, both in steady ...

2006

Spectral Entropy Feature in Full-Combination Multi-Stream for Robust ASR

Hervé Bourlard, Hemant Misra

In a recent paper, we reported promising automatic speech recognition results obtained by appending spectral entropy features to PLP features. In the present paper, spectral entropy features are used along with PLP features in the framework of multi-stream ...

2005

Spectral Entropy Feature in Full-Combination Multi-stream for Robust ASR

Hervé Bourlard, Hemant Misra

IDIAP2005

Confusion Matrix Based Entropy Correction in Multi-stream Combination

Hemant Misra

An MLP classifier outputs a posterior probability for each class. With noisy data, classification becomes less certain, and the entropy of the posteriors distribution tends to increase providing a measure of classification confidence. However, at high nois ...

2003

Confusion matrix based posterior probabilities correction

Hemant Misra

An MLP classifier outputs a posterior probability for each class. With noisy data classification becomes less certain and the entropy of the posteriors distribution tends to increase, therefore providing a measure of classification confidence. However, at ...

IDIAP2002

Learning the Decision Function for Speaker Verification

Samy Bengio

This paper explores the possibility to replace the usual thresholding decision rule of log likelihood ratios used in speaker verification systems by more complex and discriminant decision functions based for instance on Linear Regression models or Support ...

2001

A Learning Algorithm for Piecewise Linear Regression

Giancarlo Ferrari Trecate

A new learning algorithm for solving piecewise linear regression problems is proposed. It is able to train a proper multilayer feedforward neural network so as to reconstruct a target function assuming a different linear behavior on each set of a polyhedra ...

Springer, London2001