An in-depth analysis of data reduction methods for sustainable deep learning.

In recent years, deep learning has gained popularity for its ability to solve complex classification tasks. It provides increasingly better results thanks to the development of more accurate models, the availability of huge volumes of data and the improved computational capabilities of modern computers. However, these improvements in performance also bring efficiency problems, related to the storage of datasets and models, and to the waste of energy and time involved in both the training and inference processes.

Deep Learning Applied to Intracranial Hemorrhage Detection.

Intracranial hemorrhage is a serious medical problem that requires rapid and often intensive medical care. Identifying the location and type of any hemorrhage present is a critical step in the treatment of the patient. Detection of, and diagnosis of, a hemorrhage that requires an urgent procedure is a difficult and time-consuming process for human experts.

ALLERDET: A novel web app for prediction of protein allergenicity.

Allergic diseases are increasing around the world with unprecedented complexity and severity. One of the reasons is that genetically modified crops produce new potentially allergenic proteins. From this starting point, many researchers have paid attention to the development of tools to predict the allergenicity of new proteins.

Optimizing the Simplicial-Map Neural Network Architecture.

Simplicial-map neural networks are a recent neural network architecture induced by simplicial maps defined between simplicial complexes. It has been proved that simplicial-map neural networks are universal approximators and that they can be refined to be robust to adversarial attacks. In this paper, the refinement toward robustness is optimized by reducing the number of simplices (i.

Two-hidden-layer feed-forward networks are universal approximators: A constructive approach.

It is well-known that artificial neural networks are universal approximators. The classical existence result proves that, given a continuous function on a compact set embedded in an n-dimensional space, there exists a one-hidden-layer feed-forward network that approximates the function. In this paper, a constructive approach to this problem is given for the case of a continuous function on triangulated spaces.