Pasar al contenido principal

ALGORITMOS ESCALABLES DE APRENDIZAJE COMPUTACIONAL: MAS ALLA DE LA CLASIFICACION Y LA REGRESION

TIN2015-65069-C2-2-R

•
Nombre agencia financiadora Ministerio de Economía y Competitividad
Acrónimo agencia financiadora MINECO
Programa Programa Estatal de I+D+i Orientado a los Retos de la Sociedad
Convocatoria Proyectos I+D+i Retos de Investigación
Año convocatoria 2015
Plan Estatal 2013-2016 Plan Estatal de Investigación Científica y Técnica y de Innovación
Unidad de gestión Dirección General de Investigación Científica y Técnica
Centro beneficiario UNIVERSIDAD DE OVIEDO
Identificador persistente http://dx.doi.org/10.13039/501100003329

Resultados relacionados

Resultados totales (Incluyendo duplicados): 2
Encontrada(s) 1 página(s)

RUC. Repositorio da Universidade da Coruña
Publicación Contribución de congreso (ConferenceOutput)

Can data placement be effective for Neural Networks classification tasks? Introducing the Orthogonal Loss

  • Cancela, Brais
  • Bolón-Canedo, Verónica
  • Alonso-Betanzos, Amparo
Presented at: 5th International Conference on Pattern Recognition, ICPR 2020V, Virtual, Milan, 10-15 January 2021, This version of the paper has been accepted for publication. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. The final published paper is available online at: https://doi.org/10.1109/ICPR48806.2021.9412704, [Abstract]: Traditionally, a Neural Network classification training loss function follows the same principle: minimizing the distance between samples that belong to the same class, while maximizing the distance to the other classes. There are no restrictions on the spatial placement of deep features (last layer input). This paper addresses this issue when dealing with Neural Networks, providing a set of loss functions that are able to train a classifier by forcing the deep features to be projected over a predefined orthogonal basis. Experimental results shows that these `data placement' functions can overcome the training accuracy provided by the classic cross-entropy loss function., This research has been financially supported in part by European Union ERDF funds, by the Spanish Ministerio de Economía y Competitividad (research projects TIN2015-65069-C2 and PID2019-109238GB-C22), and by the Xunta de Galicia (research projects GRC2014/035 and ED431G/01). We also gratefully acknowledge the support of NVIDIA Corporation with the donation of the Titan Xp GPU used for this research. Brais Cancela acknowledges the support of the Xunta de Galicia under its postdoctoral program., Xunta de Galicia; GRC2014/035, Xunta de Galicia; ED431G/01
RUC. Repositorio da Universidade da Coruña
Publicación Contribución de congreso (ConferenceOutput)

A delayed elastic-net approach for performing adversarial attacks

  • Cancela, Brais
  • Bolón-Canedo, Verónica
  • Alonso-Betanzos, Amparo
Presented at: 5th International Conference on Pattern Recognition, ICPR 2020, Virtual, Milan, 10-15 January 2021, This version of the paper has been accepted for publication. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. The final published paper is available online at: https://doi.org/10.1109/ICPR48806.2021.9413170, [Abstract]: With the rise of the so-called Adversarial Attacks, there is an increased concern on model security. In this paper we present two different contributions: novel measures of robustness (based on adversarial attacks) and a novel adversarial attack. The key idea behind these metrics is to obtain a measure that could compare different architectures, with independence of how the input is preprocessed (robustness against different input sizes and value ranges). To do so, a novel adversarial attack is presented, performing a delayed elastic-net adversarial attack (constraints are only used whenever a successful adversarial attack is obtained). Experimental results show that our approach obtains state-of-the-art adversarial samples, in terms of minimal perturbation distance. Finally, a benchmark of ImageNet pretrained models is used to conduct experiments aiming to shed some light about which model should be selected whenever security is a role factor., This research has been financially supported in part by European Union ERDF funds, by the Spanish Ministerio de Economía y Competitividad (research project TIN2015-65069-C2), and by the Xunta de Galicia (research projects GRC2014/035 and ED431G/01). We also gratefully acknowledge the support of NVIDIA Corporation with the donation of the Titan Xp GPU used for this research. Brais Cancela acknowledges the support of the Xunta de Galicia under its postdoctoral program., Xunta de Galicia; GRC2014/035, Xunta de Galicia; ED431G/01