Browsing by Contributor "Mas Montserrat, Daniel"

Now showing items 1-8 of 8

    • Deep learning for imputation-based feature shift correction 

      Novelle Moriano, Víctor (Universitat Politècnica de Catalunya, 2022-06-27)
      Bachelor thesis
      Restricted access - confidentiality agreement

    • Learning sketches with neural networks 

      Perera Baro, Maria (Universitat Politècnica de Catalunya, 2022-06-27)
      Bachelor thesis
      Restricted access - confidentiality agreement

    • Machine learning for genome-image representation and generation 

      Comajoan Cara, Marçal (Universitat Politècnica de Catalunya, 2024-06-26)
      Bachelor thesis
      Restricted access - confidentiality agreement

    • Machine learning for human genotype-phenotype modelling and predictions 

      Luis Vidal, Aina (Universitat Politècnica de Catalunya, 2024-06-26)
      Bachelor thesis
      Restricted access - confidentiality agreement
      Covenantee:   Stanford University

    • Meta-learning for neural network weight prediction and compressive learning 

      Bonet Solé, David (Universitat Politècnica de Catalunya, 2023-09-13)
      Master thesis
      Restricted access - confidentiality agreement
      Covenantee:   Stanford University
      The rapid expansion in the size of new datasets and available data online has led to significant scaling of the size of neural models. However, training deep learning models and performing hyperparameter tuning is ...

    • Species-agnostic local ancestry inference with convolutions 

      Oriol Sàbat, Benet (Universitat Politècnica de Catalunya, 2021-10-29)
      Master thesis
      Open Access
      Local Ancestry Inference (LAI) is the high resolution prediction of ancestry (African, European, ...) across a DNA sequence. LAI is becoming increasingly important in DNA sequence analysis for the study of human ancestry ...

    • Unsupervised clustering for ancestry inference with neural networks 

      Dominguez Mantes, Albert (Universitat Politècnica de Catalunya, 2021-06-29)
      Bachelor thesis
      Open Access
      Covenantee:   Stanford University
      Caracteritzar les estructures genètiques de poblacions ha esdevingut cada cop més important donat que els estudis d'associació genètica i predictius s'han estès a cohorts cada cop més diversos. ADMIXTURE i STRUCTURE són ...

    • Unsupervised learning with applications in genomics 

      Geleta Geleta, Margarita (Universitat Politècnica de Catalunya, 2021-06-29)
      Bachelor thesis
      Restricted access - confidentiality agreement
      Deep variational autoencoders for population genetics: applications in classification, imputation, dimensionality reduction, and novel lossless data compression. In this study we show the power of variational autoencoders ...