Now showing items 1-3 of 3

    • Divide and Conquer Networks 

      Nowak Vila, Alex (Universitat Politècnica de Catalunya, 2017-05-17)
      Bachelor thesis
      Open Access
      Covenantee:   New York University. Center for Data Science
      This work considers the learning of algorithmic tasks by mere observation of input-output pairs. Rather than studying this as a black-box discrete regression problem with no assumption whatsoever on the input-output mapping, ...
    • Games in Machine Learning: Differentiable n-Player Games and Structured Planning 

      Domingo Enrich, Carles (Universitat Politècnica de Catalunya, 2019-05-30)
      Bachelor thesis
      Open Access
      Covenantee:   Courant Institute of Mathematical Sciences
      L'objectiu de l'estada és ampliar les capacitats actuals dels models d'exploració en entorns amb estructura aritmètica i geomètrica. L'estudiant serà exposat a l'avantguarda de la recerca en les àrees de deep learning i ...
    • Semi-supervised learning for training CNNs with Few Data 

      García Satorras, Víctor (Universitat Politècnica de Catalunya, 2017-10-13)
      Master thesis
      Open Access
      Covenantee:   CILVR Lab
      Although Deep Learning has successfully been applied to many fields, it relies on large amounts of data. In this work we focus on two different research lines within the context of image classification that try to deal ...