Novel techniques for harnessing symbolic and structured information into machine learning

Silvestri, Mattia (2024) Novel techniques for harnessing symbolic and structured information into machine learning, [Dissertation thesis], Alma Mater Studiorum Università di Bologna. Dottorato di ricerca in Computer science and engineering, 36 Ciclo. DOI 10.48676/unibo/amsdottorato/11518.
Documenti full-text disponibili:
[img] Documento PDF (English) - Richiede un lettore di PDF come Xpdf o Adobe Acrobat Reader
Disponibile con Licenza: Salvo eventuali più ampie autorizzazioni dell'autore, la tesi può essere liberamente consultata e può essere effettuato il salvataggio e la stampa di una copia per fini strettamente personali di studio, di ricerca e di insegnamento, con espresso divieto di qualunque utilizzo direttamente o indirettamente commerciale. Ogni altro diritto sul materiale è riservato.
Download (9MB)

Abstract

In recent years, we have assisted to a new spring of Artificial Intelligence (AI). This transformation has been characterized by a shift from the symbolic methods prevalent in the last century to a focus on sub-symbolic techniques, driven by the remarkable achievements of deep learning in areas such as computer vision and natural language processing. Despite the successes of sub-symbolic, data-driven methods, recent years have seen a growing inclination towards hybrid models that synergize symbolic and sub-symbolic approaches. This trend stems from several inherent limitations in purely data-driven systems. Firstly, these systems often redundantly learn concepts that are already part of common knowledge or are well-understood by domain experts. Secondly, data-driven methods may struggle to adhere to specific constraints, such as those dictated by natural laws or user-imposed rules, whereas symbolic methods can manage these constraints more easily. Lastly, the black-box nature of most sub-symbolic methods poses challenges in terms of interpretability and explainability, in contrast to the more transparent symbolic approaches. In the context of machine learning and deep learning, these challenges have given rise to the emergent field of informed machine learning. This new domain aims to exploit the strengths of both symbolic and sub-symbolic methods by formalizing and incorporating existing task-specific knowledge into traditional machine learning workflows. The core objective of this thesis is to explore and advance the field of informed machine learning. It presents innovative algorithms within this domain and conducts a thorough investigation of existing methodologies. The applications of these algorithms are explored in two significant areas of AI: predictive modeling and decision support systems. To validate the practical utility of these algorithms, the thesis undertakes a comprehensive empirical evaluation. The findings from these studies provide concrete evidence of the effectiveness of informed machine learning solutions in addressing the highlighted challenges.

Abstract
Tipologia del documento
Tesi di dottorato
Autore
Silvestri, Mattia
Supervisore
Dottorato di ricerca
Ciclo
36
Coordinatore
Settore disciplinare
Settore concorsuale
Parole chiave
Machine Learning, Informed Machine Learning, Physics-informed Machine Learning, Combinatorial Optimization
URN:NBN
DOI
10.48676/unibo/amsdottorato/11518
Data di discussione
24 Giugno 2024
URI

Altri metadati

Statistica sui download

Gestione del documento: Visualizza la tesi

^