The estimation of the generalization error of classifiers often relies o...
Embedding Artificial Intelligence onto low-power devices is a challengin...
Low-bit quantization of network weights and activations can drastically
...
Designing deep learning-based solutions is becoming a race for training
...
Learning deep representations to solve complex machine learning tasks ha...
Typical deep convolutional architectures present an increasing number of...
Neural networks have demonstrably achieved state-of-the art accuracy usi...
Because deep neural networks (DNNs) rely on a large number of parameters...
In this paper, we tackle the problem of incrementally learning a classif...
In most cases deep learning architectures are trained disregarding the a...
In many application domains such as computer vision, Convolutional Layer...
We introduce a novel loss function for training deep learning architectu...
Convolutional Neural Networks (CNNs) are state-of-the-art in numerous
co...
Deep learning-based methods have reached state of the art performances,
...