37 citations · 42 across the 5 of their papers we have counts for
7 papers
REVE: Regularizing Deep Learning with Variational Entropy Bound
Antoine Saporta, Yifu Chen, Michael Blot +1
Studies on generalization performance of machine learning algorithms under the scope of information theory suggest that compressed representations can guarantee good generalization…
A Characterization of Mean Squared Error for Estimator with Bagging
Martin Mihelich, Charles Dognin, Yan Shu +1
Bagging can significantly improve the generalization performance of unstable machine learning algorithms such as trees or neural networks. Though bagging is now widely used in prac…
SHADE: Information Based Regularization for Deep Learning
Michael Blot, Thomas Robert, Nicolas Thome +1
Regularization is a big issue for training deep neural networks. In this paper, we propose a new information-theory-based regularization scheme named SHADE for SHAnnon DEcay. The o…
SHADE: Information-Based Regularization for Deep Learning
Michael Blot, Thomas Robert, Nicolas Thome +1
Regularization is a big issue for training deep neural networks. In this paper, we propose a new information-theory-based regularization scheme named SHADE for SHAnnon DEcay. The o…
GoSGD: Distributed Optimization for Deep Learning with Gossip Exchange
Michael Blot, David Picard, Matthieu Cord
We address the issue of speeding up the training of convolutional neural networks by studying a distributed method adapted to stochastic gradient descent. Our parallel optimization…
Gossip training for deep learning
Michael Blot, David Picard, Matthieu Cord +1
We address the issue of speeding up the training of convolutional networks. Here we study a distributed method adapted to stochastic gradient descent (SGD). The parallel optimizati…
Maxmin convolutional neural networks for image classification
Michael Blot, Matthieu Cord, Nicolas Thome
Convolutional neural networks (CNN) are widely used in computer vision, especially in image classification. However, the way in which information and invariance properties are enco…