Pasar al contenido principal

Resultados relacionados

Resultados totales (Incluyendo duplicados): 5
Encontrada(s) 1 página(s)

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

A Machine Learning Solution for Distributed Environments and Edge Computing

  • Penas-Noce, Javier
  • Fontenla-Romero, Óscar
  • Guijarro-Berdiñas, Bertha
[Abstract] In a society in which information is a cornerstone the exploding of data is crucial. Thinking of the Internet of Things, we need systems able to learn from massive data and, at the same time, being inexpensive and of reduced size. Moreover, they should operate in a distributed manner making use of edge computing capabilities while preserving local data privacy. The aim of this work is to provide a solution offering all these features by implementing the algorithm LANN-DSVD over a cluster of Raspberry Pi devices. In this system, every node first learns locally a one-layer neural network. Later on, they share the weights of these local networks to combine them into a global net that is finally used at every node. Results demonstrate the benefits of the proposed system., This research was funded by the Spanish Secretaría de Estado de Universidades e I+D+i (Grant TIN2015-65069-C2-1-R), Xunta de Galicia (Grants ED431C2018/34, ED341D R2016/045) and FEDER funds., Xunta de Galicia; ED431C2018/34, Xunta de Galicia; ED341D R2016/045
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)

Adaptive Real-Time Method for Anomaly Detection Using Machine Learning

  • Novoa-Paradela, David
  • Fontenla-Romero, Óscar
  • Guijarro-Berdiñas, Bertha
[Abstract] Anomaly detection is a sub-area of machine learning that deals with the development of methods to distinguish among normal and anomalous data. Due to the frequent use of anomaly-detection systems in monitoring and the lack of methods capable of learning in real time, this research presents a new method that provides such online adaptability. The method bases its operation on the properties of scaled convex hulls. It begins building a convex hull, using a minimum set of data, that is adapted and subdivided along time to accurately fit the boundary of the normal class data. The model has online learning ability and its execution can be carried out in a distributed and parallel way, all of them interesting advantages when dealing with big datasets. The method has been compared to other state-of-the-art algorithms demonstrating its effectiveness., This work has been supported by Spanish Government’s Secretaría de Estado de Investigación (Grant TIN2015-65069-C2-1-R), Xunta de Galicia (Grants ED431C 2018/34 and ED431G/01) and EU FEDER funds., Xunta de Galicia; ED431C 2018/34, 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
Academica-e. Repositorio Institucional de la Universidad Pública de Navarra
Publicación Contribución de congreso (ConferenceOutput)

Análisis de redes sociales basado en las conquistas de César Borgia

  • Fumanal Idocin, Javier
  • Cordón, Óscar
  • Alonso Betanzos, Amparo
  • Bustince Sola, Humberto
  • Fernández Fernández, Francisco Javier
En este trabajo presentamos el modelado de redes sociales y detección de comunidades utilizando como base un evento histórico real, las conquistas de César Borgia en el siglo XV. Para ello, proponemos un nuevo conjunto de funciones, llamadas funciones de afinidad, disenadas para capturar la 'naturaleza de las interacciones locales entre cada par de actores en una red. Utilizando estas funciones, desarrollamos un nuevo algoritmo de detección de comunidades, el Borgia Clustering, donde las comunidades surgen naturalmente de un proceso de simulación de interacción de múltiples agentes en la red. También discutimos los efectos del tamaño y la escala de cada comunidad, y como pueden ser tomadas en cuenta en el proceso de simulación. Finalmente, comparamos nuestra detección de comunidades con otros algoritmos representativos, encontrando resultados favorables a nuestra propuesta., El trabajo de Javier Fumanal Idocin y Humberto Bustince ha sido financiado por el proyecto PID2019-108392GB-I00 (AEI/10.13039/ 501100011033). El trabajo de Oscar Cordón ha sido financiado por el Gobierno de España, EXASOCO (PGC2018-101216-B-I00), incluyendo fondos de desarrollo regional europeo (ERDF). La investigación de Amparo Alonso Betanzos ha sido parcialmente financiado por el Ministerio de Economía y Competitividad de España (TIN2015-65069-C2-1-R), por los fondos europeos FEDER y por la Consellería de Industria de la Xunta de Galicia (GRC2014 /035). El trabajo de María Minárová ha sido financiado por los proyectos APVV-17-0066, and APVV-18-0052.