As machine learning (ML) models and datasets increase in complexity, the demand for
methods that enhance explainability and interpretability becomes paramount. Prototypes, by …

In the domain of non-generative visual counterfactual explanations (CE), traditional
techniques frequently involve the substitution of sections within a query image with …

The graph model is nowadays largely adopted to model a wide range of knowledge and
data, spanning from social networks to knowledge graphs (KGs), representing a successful …

Counterfactual explanations (CEs) based on concepts are explanations that consider
alternative scenarios to understand which high-level semantic features contributed to …

Gender bias in machine translation (MT) systems poses significant challenges that often
result in the reinforcement of harmful stereotypes. Especially in the labour domain where …

Counterfactuals have been established as a popular explainability technique which
leverages a set of minimal edits to alter the prediction of a classifier. When considering …

EXplainable AI has received significant attention in recent years. Machine learning models
often operate as black boxes, lacking explainability and transparency while supporting …

Περίληψη Η παρούσα διατριβή εμβαθύνει στον πολύπλοκο τομέα του virality και
παραγόντων που το καθορίζουν, εστιάζοντας στα βίντεο του YouTube. Τα εισαγωγικά …

Περίληψη Τα Νευρωνικά Δίκτυα Γράφων (ΝΔΓ) έχουν αναδειχθεί ως ένα βασικό μοντέλο στον
τομέα της μηχανικής μάθησης, λόγω της μοναδικής τους ικανότητας να χειρίζονται δεδομένα …

Περίληψη Η τεχνητή νοημοσύνη υπέστη εκρηκτική εξέλιξη τα τελευταία χρόνια. Με κινητήριο
δύναμη την τεχνολογία της βαθιάς μάθησης, η τεχνητή νοημοσύνη βρίσκει εφαρμογή σε …