Master in Artificial Intelligence - MAI
Recent Submissions
-
Factors associated to mortality in patients of the first wave infected by COVID-19 in Spain
(Universitat Politècnica de Catalunya, 2021-06-28)
Master thesis
Open AccessThis project aims to carrying out an in-depth, retrospective and multicen-ter analysis on the distribution, correlations, missing values and survival of covid-infected patients in Spain. Artificial intelligence (AI) has ... -
TimeSeq: sequences with normalized time information for Seq2Seq translation task
(Universitat Politècnica de Catalunya, 2021-07-02)
Master thesis
Open AccessDuring last years, researchers have focused on developing Deep Learning models to translate natural language questions to SQL structured queries, what is known as the "text-to-sql" translation task. By 2020, DL models have ... -
RGB to 3D garment reconstruction using UV map representations
(Universitat Politècnica de Catalunya, 2021-06-28)
Master thesis
Open AccessPredicting the geometry of a 3D object from just a single image or viewpoint is an intrinsic human feature extremely challenging for machines. For years, in an attempt to solve this problem, different computer vision ... -
Scanflow: A learning-symbolic framework for offline and online debugging of Machine Learning workflows using multidigraph and agent structures
(Universitat Politècnica de Catalunya, 2021-06-28)
Master thesis
Restricted access - author's decision -
Fracture detection and explainability in deep learning models
(Universitat Politècnica de Catalunya, 2021-06-25)
Master thesis
Open AccessThis 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 ... -
Personality regression from multimodal dyadic data
(Universitat Politècnica de Catalunya, 2021-06-21)
Master thesis
Open AccessPersonality is made up of broad traits that are relatively stable over time and allow to differentiate one person from another. The most widely accepted theory to model personality is the Big-Five model that defines the ... -
Topic modeling and bias analysis in a large scale spanish text dataset
(Universitat Politècnica de Catalunya, 2021-04-18)
Master thesis
Open AccessIn a world where data generation is doubled continuously, the ability to efficiently classify and analyze large amounts of data is key to success. In this thesis, we will describe the implementation of a distributed topic ... -
Linguistics4fairness: neutralizing Gender Bias in neural machine translation by introducing linguistic knowledge
(Universitat Politècnica de Catalunya, 2021-04-29)
Master thesis
Open AccessNeural Machine Translation has the power of learning from a large collection of data, which allows it to learn translations effectively and without requiring linguistic knowledge from the languages to translate. The main ... -
Learning recursive goal proposal: a hierarchical reinforcement learning approach
(Universitat Politècnica de Catalunya, 2021-04-28)
Master thesis
Open Access
Covenantee: Universitat de Barcelona / Universitat Rovira i Virgili. Escola Tècnica Superior d'EnginyeriaReinforcement Learning's unique way of learning has led to remarkable successes like Alpha Zero or Alpha Go, mastering the games of Chess and Go, and being able to beat the respective World Champions. Notwithstanding, ... -
Learning to run naturally: guiding policies with the Spring-Loaded Inverted Pendulum
(Universitat Politècnica de Catalunya, 2021-04-28)
Master thesis
Open Access
Covenantee: Universitat de Barcelona / Universitat Rovira i VirgiliIn this work, we proposed a new approach for learning legged locomotion for any legged robot, in the sagittal plane, by using a combination of classical control techniques and reinforcement learning. Specifically, we use ... -
On Meta-Reinforcement Learning in task distributions with varying dynamics
(Universitat Politècnica de Catalunya, 2021-04-28)
Master thesis
Open Access
Covenantee: Universitat de Barcelona / Universitat Rovira i VirgiliMeta-reinforcement learning has the potential to enable artificial agents to master new skills with improved sample-efficiency by leveraging previous learning experience in tasks that are diverse but share common structure. ... -
Evolving cooperation in multi-agent systems
(Universitat Politècnica de Catalunya, 2021-04-28)
Master thesis
Open Access
Covenantee: Universitat de Barcelona / Universitat Rovira i VirgiliApplications of deep reinforcement learning in multi-agent systems are a rapidly developing scientific field that focuses on constructing computational frameworks and models for how various agents can interact efficiently ...
RSS 1.0