Multilayer neural networks were first proposed more than three decades ago, and various architectures and parameterizations were explored since. Recently, graphics processing units enabled very efficient neural network training, and allowed training much larger networks on larger datasets, dramatically improving performance on various supervised learning tasks. However, the generalization is still far from human level, and it is difficult to understand on what the decisions made are based. To improve on generalization and understanding we revisit the problems of weight parameterizations in deep neural networks. We identify the most important, to our mind, problems in modern architectures: network depth, parameter efficiency, and learning mu...
Over the past few years, deep neural networks have been at the center of attention in machine learn...
A Deep Convolutional Neural Network Architecture for effective Image AnalysisThis master thesis pres...
Deep learning applications are rapidly expanding and show no signs of slowing down. Neural network t...
Multilayer neural networks were first proposed more than three decades ago, and various architecture...
In this thesis, we study the transfer of Convolutional Neural Networks (CNN) trained on natural imag...
Neural network models and deep models are one of the leading and state of the art models in machine ...
Juillet-Septembre 1997In my PhD Thesis ,three constructive algorithms were developed. These algorith...
Over the last decades, machine learning revolutionised our daily lives from recommendation systems t...
This thesis studies empirical properties of deep convolutional neural networks, and in particular th...
Despite numerous successes in a wide range of industrial and scientific applications, the learning p...
The increased availability of large amounts of data, from images in social networks, speech waveform...
The structure of a neural network determines to a large extent its cost of training and use, as well...
This thesis explores the use of structured losses in two different domains. In the first contributio...
Artificial intelligence has been an ultimate design goal since the inception of computers decades ag...
Les réseaux de neurones à convolution sont des algorithmes d’apprentissage flexibles qui tirent effi...
Over the past few years, deep neural networks have been at the center of attention in machine learn...
A Deep Convolutional Neural Network Architecture for effective Image AnalysisThis master thesis pres...
Deep learning applications are rapidly expanding and show no signs of slowing down. Neural network t...
Multilayer neural networks were first proposed more than three decades ago, and various architecture...
In this thesis, we study the transfer of Convolutional Neural Networks (CNN) trained on natural imag...
Neural network models and deep models are one of the leading and state of the art models in machine ...
Juillet-Septembre 1997In my PhD Thesis ,three constructive algorithms were developed. These algorith...
Over the last decades, machine learning revolutionised our daily lives from recommendation systems t...
This thesis studies empirical properties of deep convolutional neural networks, and in particular th...
Despite numerous successes in a wide range of industrial and scientific applications, the learning p...
The increased availability of large amounts of data, from images in social networks, speech waveform...
The structure of a neural network determines to a large extent its cost of training and use, as well...
This thesis explores the use of structured losses in two different domains. In the first contributio...
Artificial intelligence has been an ultimate design goal since the inception of computers decades ag...
Les réseaux de neurones à convolution sont des algorithmes d’apprentissage flexibles qui tirent effi...
Over the past few years, deep neural networks have been at the center of attention in machine learn...
A Deep Convolutional Neural Network Architecture for effective Image AnalysisThis master thesis pres...
Deep learning applications are rapidly expanding and show no signs of slowing down. Neural network t...