Nous argumentons que l'estimation de l'information mutuelle entre des ensembles de variables aléatoires continues de hautes dimensionnalités peut être réalisée par descente de gradient sur des réseaux de neurones. Nous présentons un estimateur neuronal de l'information mutuelle (MINE) dont la complexité croît linéairement avec la dimensionnalité des variables et la taille de l'échantillon, entrainable par retro-propagation, et fortement consistant au sens statistique. Nous présentons aussi une poignée d'application ou MINE peut être utilisé pour minimiser ou maximiser l'information mutuelle. Nous appliquons MINE pour améliorer les modèles génératifs adversariaux. Nous utilisons aussi MINE pour implémenter la méthode du goulot d'étranglemen...
Künstliche neuronale Netze werden in der Regel durch eine wiederholte Präsentation von Trainingspatt...
The goal of this thesis was to investigate how information theory could be used to analyze artificia...
International audienceNowadays, neural networks are largely used in signal and image processin...
Dans cette thése, nous proposant un nouvel algorithme de séparation aveugle de sources, basé sur l'o...
Cette thèse traite de mémoires associatives neuro-inspirées. Une extension des réseaux de neurones r...
Neural networks can be regarded as statistical models, and can be analysed in a Bayesian framework. ...
There is a need to better understand how generalization works in a deep learning model. The goal of ...
Mutual Information (MI) has been widely used as a loss regularizer for training neural networks. Thi...
We introduce the Redundant Information Neural Estimator (RINE), a method that allows efficient estim...
The Information Bottleneck theory provides a theoretical and computational framework for finding app...
The present paper1 aims to propose a new type of information-theoretic method to maximize mutual inf...
MEng (Computer en Electronic Engineering), North-West University, Potchefstroom CampusThe generalisa...
This paper presents a new algorithm based on the theory of mutual information and information geomet...
Neural network models able to approximate and sample high-dimensional probability distributions are ...
The goal of neural processing assemblies is varied, and in many cases still rather unclear. However,...
Künstliche neuronale Netze werden in der Regel durch eine wiederholte Präsentation von Trainingspatt...
The goal of this thesis was to investigate how information theory could be used to analyze artificia...
International audienceNowadays, neural networks are largely used in signal and image processin...
Dans cette thése, nous proposant un nouvel algorithme de séparation aveugle de sources, basé sur l'o...
Cette thèse traite de mémoires associatives neuro-inspirées. Une extension des réseaux de neurones r...
Neural networks can be regarded as statistical models, and can be analysed in a Bayesian framework. ...
There is a need to better understand how generalization works in a deep learning model. The goal of ...
Mutual Information (MI) has been widely used as a loss regularizer for training neural networks. Thi...
We introduce the Redundant Information Neural Estimator (RINE), a method that allows efficient estim...
The Information Bottleneck theory provides a theoretical and computational framework for finding app...
The present paper1 aims to propose a new type of information-theoretic method to maximize mutual inf...
MEng (Computer en Electronic Engineering), North-West University, Potchefstroom CampusThe generalisa...
This paper presents a new algorithm based on the theory of mutual information and information geomet...
Neural network models able to approximate and sample high-dimensional probability distributions are ...
The goal of neural processing assemblies is varied, and in many cases still rather unclear. However,...
Künstliche neuronale Netze werden in der Regel durch eine wiederholte Präsentation von Trainingspatt...
The goal of this thesis was to investigate how information theory could be used to analyze artificia...
International audienceNowadays, neural networks are largely used in signal and image processin...