Learning processes by exploiting restricted domain knowledge is an impor...
Compressing deep networks is essential to expand their range of applicat...
Random forests have been widely used for their ability to provide so-cal...
Transfer Learning (TL) is an efficient machine learning paradigm that al...
This paper presents a model-agnostic ensemble approach for supervised
le...
Explanation techniques are commonly evaluated using human-grounded metho...
This paper introduces four new algorithms that can be used for tackling
...
We study the generalization properties of pruned neural networks that ar...
In this work, we investigate multi-task learning as a way of pre-trainin...
In this work, we investigate multi-task learning as a way of pre-trainin...
This paper makes one step forward towards characterizing a new family of...
In many applications of supervised learning, multiple classification or
...
We introduce a novel Deep Reinforcement Learning (DRL) algorithm called ...
Dealing with datasets of very high dimension is a major challenge in mac...
In many cases, feature selection is often more complicated than identify...
In this work, we propose a simple yet effective solution to the problem ...
Networks are ubiquitous in biology and computational approaches have bee...
We adapt the idea of random projections applied to the output space, so ...