To Be fAIr or Not to Be: Using AI for the Good of Citizens

Autor: Atia Cortés, Abraham Sánchez, Dario Garcia-Gasulla, Ulises Cortés, E. Ulises Moya-Sánchez, Cristian Barrué

Publikováno v: IEEE Technology and Society Magazine. 40:55-70

In the last decade, there has been an explosion in the progress and applications of artificial intelligence (AI) in our society. For the first time, the applications of AI have left the laboratory to reach society in a broad, visible, and relevant wa

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::95b46e0a1f393b0047d4a9e2a2bdaae0
https://doi.org/10.1109/mts.2021.3056173

A bio-inspired quaternion local phase CNN layer with contrast invariance and linear sensitivity to rotation angles

Autor: Sebastià Xambó-Descamps, Ulises Cortés, Sebastián Salazar-Colores, Abraham Sánchez Pérez, Jorge Martínez-Ortega, E. Ulises Moya-Sánchez

Publikováno v: Pattern Recognition Letters. 131:56-62

Deep learning models have been particularly successful with image recognition using Convolutional Neural Networks (CNN). However, the learning of a contrast invariance and rotation equivariance response may fail even with very deep CNNs or by large d

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::ed828496e48fcc253b41e9578192fa10
https://doi.org/10.1016/j.patrec.2019.12.001

A trainable monogenic ConvNet layer robust in front of large contrast changes in image classification

Autor: Sanchez Abraham, E. Ulises Moya-Sánchez, Sebastià Xambó-Descamps, Sebastián Salazar-Colores, Ulises Cortés

Publikováno v: IEEE Access, Vol 9, Pp 163735-163746 (2021)
UPCommons. Portal del coneixement obert de la UPC
Universitat Politècnica de Catalunya (UPC)

Convolutional Neural Networks (ConvNets) at present achieve remarkable performance in image classification tasks. However, current ConvNets cannot guarantee the capabilities of the mammalian visual systems such as invariance to contrast and illuminat

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::dccb389c92221d71c9c85918b20fd6bb

Data Augmentation for Deep Learning of Non-mydriatic Screening Retinal Fundus Images

Autor: Abraham Sánchez, Dario Garcia-Gasulla, Jonathan Moreno, Miguel A Zapata, E. Ulises Moya-Sánchez, Jesús Labarta, Ulises Cortés, Eduard Ayguadé, Ferran Parrés

Publikováno v: Communications in Computer and Information Science ISBN: 9783030104474
UPCommons. Portal del coneixement obert de la UPC
Universitat Politècnica de Catalunya (UPC)

Fundus image is an effective and low-cost tool to screen for common retinal diseases. At the same time, Deep Learning (DL) algorithms have been shown capable of achieving similar or even better performance accuracies than physicians in certain image

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::78da71546353c9e1d348c2b5733c3f19
https://doi.org/10.1007/978-3-030-10448-1_18

Introduction and Limitations of Deep Learning II Introduction and Limitations of Deep Learning II 2 v1.1

Autor: E Ulises Moya-Sánchez, Sánchez, Abraham, Cortés, Ulises

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::4db9cbc068e79a1f6bba0dd8ecdd6553