Modeling uncertainty for reliable probabilistic modeling in deep learning and beyond

• Autores: Juan Maroñas Molano
• Directores de la Tesis: Daniel Ramos Castro (dir. tes.), Roberto Paredes Palacios (dir. tes.)
• Lectura: En la Universitat Politècnica de València ( España ) en 2022
• Idioma: español
• Tribunal Calificador de la Tesis: Francisco Casacuberta Nolla (presid.), Daniel Hernández Lobato (secret.), Mauricio A. Álvarez López (voc.)
• Programa de doctorado: Programa de Doctorado en Informática por la Universitat Politècnica de València
• Materias:
  • Ciencias tecnológicas
    • Tecnología de los ordenadores
      • Sistemas de reconocimiento de caracteres
      • Diseño de sistemas de calculo
    • Procesos tecnológicos
• Enlaces
  • Tesis en acceso abierto en: RiuNet
• Resumen

  • This thesis is framed at the intersection between modern Machine Learning techniques, such as Deep Neural Networks, and reliable probabilistic modeling. In many machine learning applications, we do not only care about the prediction made by a model (e.g. this lung image presents cancer) but also in how confident is the model in making this prediction (e.g. this lung image presents cancer with 67% probability). In such applications, the model assists the decision-maker (in this case a doctor) towards making the final decision. As a consequence, one needs that the probabilities provided by a model reflects the true underlying set of outcomes, otherwise the model is useless in practice. When this happens, we say that a model is perfectly calibrated.

    In this thesis three ways are explored to provide more calibrated models. First, it is shown how to calibrate models implicitly, which are decalibrated by data augmentation techniques. A cost function is introduced that solves this decalibration taking as a starting point the ideas derived from decision making with Bayes' rule. Second, it shows how to calibrate models using a post-calibration stage implemented with a Bayesian neural network. Finally, and based on the limitations studied in the Bayesian neural network, which we hypothesize that came from a mispecified prior, a new stochastic process is introduced that serves as a priori distribution in a Bayesian inference problem.