Now showing items 1-10 of 10

    • 2013-2014 Severo Ochoa : Research Seminar Lectures at BSC : book of abstracts 

      Vázquez, Mariano; Goñi Macià, Ramon; Arís, Ruth; Jorba Casellas, Oriol; Schutgens, Nick; Kranzlmüller, Dieter; Schulz, Martin; Shi, Yong; Strassburg, Janko; Faraboschi, Paolo; Aguado Sierra, Jazmín; Saen-Oon, Suwipa; Walker, Ross C.; Cetto, Raul; Suzumura, Toyotaro; Di Tomaso, Enza; Patt, Yale; Zoppè, Monica; Jeannot, Emmanel; Klasky, Scott A. (Barcelona Super Computer Center. Education & Training team, 2014-08-05)
      Conference report
      Open Access
    • A visual embedding for the unsupervised extraction of abstract semantics 

      García Gasulla, Dario; Ayguadé Parra, Eduard; Labarta Mancho, Jesús José; Béjar Alonso, Javier; Cortés García, Claudio Ulises; Suzumura, Toyotaro; Chen, R (2017-05-01)
      Article
      Open Access
      Vector-space word representations obtained from neural network models have been shown to enable semantic operations based on vector arithmetic. In this paper, we explore the existence of similar information on vector ...
    • An industrial point of view on next-generation graph computing 

      Suzumura, Toyotaro (Barcelona Supercomputing Center, 2017-09-10)
      Conference report
      Open Access
      In the era of big data, the graph models are becoming very popular data models as they can naturally represent many real world problems. Over the past several years, the efforts to accelerate graph computing on supercomputing ...
    • An out-of-the-box full-network embedding for convolutional neural networks 

      Garcia-Gasulla, Dario; Vilalta Arias, Armand; Parés, Ferran; Ayguadé Parra, Eduard; Labarta Mancho, Jesús José; Cortés García, Claudio Ulises; Suzumura, Toyotaro (Institute of Electrical and Electronics Engineers (IEEE), 2018)
      Conference report
      Open Access
      Features extracted through transfer learning can be used to exploit deep learning representations in contexts where there are very few training samples, where there are limited computational resources, or when the tuning ...
    • Building graph representations of deep vector embeddings 

      Garcia Gasulla, Dario; Vilalta Arias, Armand; Parés Pont, Ferran; Moreno Vázquez, Jonatan; Ayguadé Parra, Eduard; Labarta Mancho, Jesús José; Cortés García, Claudio Ulises; Suzumura, Toyotaro (Association for Computational Linguistics, 2017)
      Conference lecture
      Open Access
      Patterns stored within pre-trained deep neural networks compose large and powerful descriptive languages that can be used for many different purposes. Typically, deep network representations are implemented within vector ...
    • Efficient and versatile data analytics for deep networks 

      Garcia Gasulla, Dario; Moreno Vázquez, Jonatan; Espinosa-Oviedo, Javier A.; Conejero, Javier; Vargas-Solar, Genoveva; Badia Sala, Rosa Maria; Cortés García, Claudio Ulises; Suzumura, Toyotaro (Barcelona Supercomputing Center, 2015-05-05)
      Conference report
      Open Access
      Deep networks (DN) perform cognitive tasks related with image and text at human-level. To extract and exploit the knowledge coded within these networks we propose a framework which combines state-of-the-art technology in ...
    • Fluid communities: a competitive, scalable and diverse community detection algorithm 

      Parés Sabatés, Ferran; García Gasulla, Darío; Vilalta Arias, Armand; Moreno, Jonatan; Ayguadé Parra, Eduard; Labarta Mancho, Jesús José; Cortés García, Claudio Ulises; Suzumura, Toyotaro (Springer, 2017)
      Conference report
      Restricted access - publisher's policy
      We introduce a community detection algorithm (Fluid Communities) based on the idea of fluids interacting in an environment, expanding and contracting as a result of that interaction. Fluid Communities is based on the ...
    • Full-network embedding in a multimodal embedding pipeline 

      Vilalta Arias, Armand; Garcia Gasulla, Dario; Parés Pont, Ferran; Moreno Vázquez, Jonatan; Ayguadé Parra, Eduard; Labarta Mancho, Jesús José; Cortés García, Claudio Ulises; Suzumura, Toyotaro (Association for Computational Linguistics, 2017)
      Conference lecture
      Open Access
      The current state-of-the-art for image annotation and image retrieval tasks is obtained through deep neural networks, which combine an image representation and a text representation into a shared embedding space. In this ...
    • On the behavior of convolutional nets for feature extraction 

      Garcia-Gasulla, Dario; Parés Pont, Ferran; Vilalta Arias, Armand; Moreno, Jonatan; Ayguadé Parra, Eduard; Labarta Mancho, Jesús José; Cortés García, Claudio Ulises; Suzumura, Toyotaro (2018-03)
      Article
      Open Access
      Deep neural networks are representation learning techniques. During training, a deep net is capable of generating a descriptive language of unprecedented size and detail in machine learning. Extracting the descriptive ...
    • On the representativeness of convolutional neural networks layers 

      García Gasulla, Darío; Moreno, Jonatan; Ramos-Pollan, Raúl; Casadiegos Barrios, Romel; Béjar Alonso, Javier; Cortés García, Claudio Ulises; Ayguadé Parra, Eduard; Labarta Mancho, Jesús José; Suzumura, Toyotaro (IOS PRESS EBOOKS, 2016)
      Part of book or chapter of book
      Open Access
      Convolutional Neural Networks (CNN) are the most popular of deep network models due to their applicability and success in image processing. Although plenty of effort has been made in designing and training better discriminative ...