Recent Submissions

  • Exploring techniques to train large images using Deep Learning 

    Garcia Romero, Lluís (Universitat Politécnica de Catalunya, 2019-12)
    Bachelor thesis
    Open Access
    In this project, we present two new problems to solve and our approaches to achieve it, using the MET Museum images dataset. We are facing a classification problem, predicting the original culture of each image, and a ...
  • 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 ...
  • Chat-bot for Garmin Maroc 

    Gnaou, Soraya (Universitat Politècnica de Catalunya, 2019-07-01)
    Master thesis
    Restricted access - confidentiality agreement
  • Right whales up-call detection using deep classifiers over underwater noisy recordings 

    Rodriguez Molinuevo, Jorge (Universitat Politècnica de Catalunya, 2019-10-21)
    Master thesis
    Open Access
    Covenantee:  Universitat de Barcelona. Facultat de Matemàtiques i Informàtica / Universitat Rovira i Virgili. Escola Tècnica Superior d'Enginyeria
    This project evaluates the potential of Convolutional Neural Networks in classifying Right Whales' Up-Calls from short audio clips of environmental sounds. Two deep models with different architectures are presented evaluating ...
  • Generative Video Face Reenactment by AUs and Gaze Regularization 

    Famadas, Josep (Universitat Politècnica de Catalunya, 2019-10-15)
    Master thesis
    Open Access
    Covenantee:  Universitat de Barcelona. Facultat de Matemàtiques i Informàtica / Universitat Autònoma de Barcelona
    In this work, we propose an encoder-decoder-like architecture to perform face reenact- ment in image sequences. Our goal is to transfer the training subject identity to a given test subject, regularazing the generation ...
  • Speeding up Reinforcement Learning with Learned Models 

    Pou Mulet, Bartomeu (Universitat Politècnica de Catalunya, 2019-10-16)
    Master thesis
    Open Access
    In this master thesis, we have tried to solve two of most prominent Reinforcement Learning problems: sparse rewards and sample efficiency. The combination of Model Based Reinforcement Learning, Hindsight Experience Replay ...
  • Log-Distributional Approach for Learning Covariate Shift Ratios 

    Bernárdez Gil, Guillermo (Universitat Politècnica de Catalunya, 2019-10-21)
    Master thesis
    Open Access
    Distributional Reinforcement Learning theory suggests that distributional fixed points could play a fundamental role to learning non additive value functions. In particular, we propose a distributional approach for learning ...
  • Gaming and Healthcare. An intelligent way to help our elders. 

    Martínez Sanahuja, Laura (Universitat Politècnica de Catalunya, 2019-06)
    Master thesis
    Open Access
    Covenantee:  Universitat de Barcelona. Facultat de Matemàtiques i Informàtica / Universitat Rovira i Virgili. Escola Tècnica Superior d'Enginyeria
    The purpose of this thesis is to develop an application to evaluate the physical and mental state of the elderly over time using different games that interact with different abilities. It will keep the progress of the ...
  • A Photo-realistic Voice-bot 

    Alexander, Jorge (Universitat Politècnica de Catalunya, 2019-07-01)
    Master thesis
    Open Access
    Covenantee:  Universitat de Barcelona. Facultat de Matemàtiques i Informàtica / Universitat Rovira i Virgili. Escola Tècnica Superior d'Enginyeria
    Technology is at the point where systems are capable of synthesizing video of human actors indistinguishably from ones in which the actor is present. This research investigates whether or not it is possible to use this ...
  • Study and Experimentation of Gender Bias in Co-reference Resolution 

    Alfaro, Felipe (Universitat Politècnica de Catalunya, 2019-06-18)
    Master thesis
    Open Access
    Covenantee:  Universitat de Barcelona. Facultat de Matemàtiques i Informàtica / Universitat Rovira i Virgili. Escola Tècnica Superior d'Enginyeria
    Co-reference resolution is an important part of natural language understanding and it's been affected by the current corpora lacking in diversity. This project presents the implementation of two models for masked language ...
  • Virtual try-on with generative adversarial networks 

    Arcos López, Pablo (Universitat Politècnica de Catalunya, 2019-06)
    Master thesis
    Restricted access - confidentiality agreement
  • 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 ...

View more