Logic Tensor Networks for Knowledge-Infused Learning: Foundations, Experiments, and Applications

dc.contributor.advisorPujol Vila, Oriol
dc.contributor.authorGuiot Cusidó, Quim
dc.date.accessioned2026-10-23T11:56:54Z
dc.date.available2026-10-23T11:56:54Z
dc.date.issued2026-06-27
dc.descriptionTreballs finals del Màster de Fonaments de Ciència de Dades, Facultat de matemàtiques, Universitat de Barcelona. Any: 2026. Tutor: Oriol Pujol Vila
dc.description.abstractThis thesis investigates Logic Tensor Networks (LTN) as a neurosymbolic framework for knowledge infused learning, focusing on their theoretical underpinnings, practical behavior, and applicability to real world tasks. We first present a self contained exposition of Real Logic, detailing how symbols are grounded into tensors, how fuzzy logical operators are instantiated in a differentiable setting, and how learning is framed as maximizing the satisfiability of a Real Logic theory. Building on this foundation, we design a controlled 1D regression problem where a neural model predicts a person’s weight from their height under different logical configurations. Through three experiments (baseline regression, a favorable monotonicity axiom, and a deliberately misleading monotonicity axiom) we study how prior knowledge encoded as axioms affects in distribution performance, out of distribution generalization, and the truth degree of queries. The results show that well aligned axioms can improve both regression accuracy and robustness, while incorrect axioms systematically degrade performance, highlighting LTN as a sensitive interface between data and prior knowledge. Finally, we explore a real life recommender system case study, where LTN are used to mitigate data sparsity by injecting genre based user preferences into a matrix factorization pipeline. Altogether, this work illustrates both the promise and the risks of knowledge infused learning with LTN. The following link will take the lector to the GitHub Repository containing the performed and developed experiments discussed on chapter 4: My GitHub Repository. URL to copy paste on your browser: https://github.com/srguiot14/Logic-Tensor-Networks-for-Knowledge-Infused-Learning-Foundations-Experiments-and-Applications.
dc.format.extentx p.
dc.format.mimetypeapplication/pdf
dc.identifier.urihttps://hdl.handle.net/2445/232297
dc.language.isoeng
dc.rightsmemòria: cc-by-nc-nd (c) Guiot Cusidó, Quim, 2026
dc.rightscodi: Apache (c) Guiot Cusidó, Quim, 2026
dc.rights.accessRightsinfo:eu-repo/semantics/openAccess
dc.rights.urihttp://creativecommons.org/licenses/by-nc-nd/3.0/es/
dc.rights.urihttp://www.apache.org/licenses/LICENSE-2.0
dc.subject.classificationLògica difusa
dc.subject.classificationAprenentatge automàtic
dc.subject.classificationXarxes neuronals (Informàtica)
dc.subject.classificationProgramari
dc.subject.classificationTreballs de fi de màster
dc.subject.otherFuzzy logic
dc.subject.otherMachine learning
dc.subject.otherNeural networks (Computer science)
dc.subject.otherComputer software
dc.subject.otherMaster's thesis
dc.titleLogic Tensor Networks for Knowledge-Infused Learning: Foundations, Experiments, and Applications
dc.typeinfo:eu-repo/semantics/masterThesis

Fitxers

Paquet original

Mostrant 1 - 2 de 2
Carregant...
Miniatura
Nom:
TFM_Guiot_Cusido_Joaquim.pdf
Mida:
474.29 KB
Format:
Adobe Portable Document Format
Carregant...
Miniatura
Nom:
Codi.zip
Mida:
2.38 MB
Format:
ZIP file