Now showing items 1-12 of 12

    • A study of neural behavioral differences among CNN architectures 

      Gimenez Abalos, Victor (Universitat Politècnica de Catalunya, 2019-06)
      Bachelor thesis
      Open Access
      La extracción de activaciones neuronales de una red neuronal convolucional permite reutilizar representaciones internas de un modelo pre-entrenado para resolver problemas nuevos, incluso no relacionados con el problema ...
    • Adapting the smart python agent development environment for parallel computing 

      Gnatyshak, Dmitry (Universitat Politècnica de Catalunya, 2019-04-15)
      Master thesis
      Open Access
      Covenantee:   Universitat Rovira i Virgili / Universitat de Barcelona
    • Computing methods for parallel processing and analysis on complex networks 

      Vázquez Benítez, Luis Andrés (Universitat Politècnica de Catalunya, 2015-05-05)
      Master thesis
      Open Access
      Nowadays to solve some problems is required to model complex systems to simulate and understand its behavior. A good example of one of those complex systems is the Facebook Social Network, this system represents people ...
    • Evaluating the Robustness of GAN-Based Inverse Reinforcement Learning Algorithms 

      Heidecke, Johannes (Universitat Politècnica de Catalunya, 2019-01-15)
      Master thesis
      Open Access
      Covenantee:   Universitat de Barcelona / Universitat Rovira i Virgili
      We evaluate the robustness of reward functions learned with IRL, when transferred to similar tasks. We exceed state of the art results for one benchmark task and solve another one for the first time. Modifications are ...
    • Fracture detection and explainability in deep learning models 

      Giménez Abalos, Víctor (Universitat Politècnica de Catalunya, 2021-06-25)
      Master thesis
      Open Access
      This thesis has been developed in the context of a collaboration project between health insurance company for work accidents Asepeyo and the Barcelona Supercomputing Center (BSC). The target of this project is the creation ...
    • Glyph 

      Berns, Sebastian (Universitat Politècnica de Catalunya, 2018-10)
      Master thesis
      Open Access
      Covenantee:   Universitat de Barcelona. Facultat de Matemàtiques i Informàtica / Universitat Rovira i Virgili. Escola Tècnica Superior d'Enginyeria
      In this work, I propose a typographic style transfer methodology, based on a custom trained convolutional neural network, with the intention to generate the unobserved characters of a digital typeface in the corresponding ...
    • Implementació d'un sistema portable multimodal basat en Deep Learning 

      Abella Gassol, Adrià (Universitat Politècnica de Catalunya, 2016)
      Bachelor thesis
      Open Access
    • Random Forest as a tumour genetic marker extractor 

      Pérez Arnal, Raquel Leandra (Universitat Politécnica de Catalunya, 2019-10)
      Master thesis
      Open Access
      Covenantee:   Universitat de Barcelona. Facultat de Matemàtiques i Informàtica / Universitat Rovira i Virgili. Escola Tècnica Superior d'Enginyeria
      Identifying tumour genetic markers is an essential task for biomedicine. In this thesis, we analyse a dataset of chromosomal rearrangements of cancer samples and present a methodology for extracting genetic markers from ...
    • SPiDer: Smart Pill Dispenser 

      Moreno Vázquez, Jonatan (Universitat Politècnica de Catalunya, 2013-04-29)
      Master thesis (pre-Bologna period)
      Open Access
      Aquest projecte proposa el sistema SPiDer el qual te l'objectiu d'assistir a la gent gran en el procés de medicar-se evitant els problemes associats amb la baixa adherència existent actualment amb els calendaris farmacològics ...
    • Studying the characterization of deep CNN neurons 

      Garriga Estradé, Carles (Universitat Politècnica de Catalunya, 2019-07-02)
      Master thesis
      Open Access
      This master thesis has studied the characteristics of deep conventional neurons present in a Deep CNN. Three approaches towards finding different behaviours in the architecture have been introduced: a first supervised to ...
    • Using unaltered, variable sized and high-resolution images for training fully-convolutional networks 

      Fourkioti, Olga (Universitat Politècnica de Catalunya, 2019-06)
      Master thesis
      Open Access
      Motivated by the usefulness of high resolution images in a broad range of applications, such as medical imaging, astronomy and video surveillance, in this thesis we investigate training a convolutions neural network with ...
    • Wordnet y Deep Learning: Una posible unión 

      Pérez Arnal, Raquel Leandra (Universitat Politècnica de Catalunya, 2018-01)
      Bachelor thesis
      Open Access
      Uno de los campos de estudio en alza del momento es el de Machine Learning, una rama de la inteligencia artificial que da a ciertos programas la habilidad de aprender autónoma-mente a partir de datos. Al no programar de ...