Selective rationalization via genetic-based learning: extending the GenSPP architecture with the CMA-ES algorithm

Clotan, Paul Ioan (2025) Selective rationalization via genetic-based learning: extending the GenSPP architecture with the CMA-ES algorithm. [Laurea magistrale], Università di Bologna, Corso di Studio in Artificial intelligence [LM-DM270], Documento full-text non disponibile
Il full-text non è disponibile per scelta dell'autore. (Contatta l'autore)

Abstract

Deep learning models often lack transparency, preventing their adoption in high-stakes decision-making domains. The Gen-SPP framework addresses this by generating sparse, human-readable rationales for classification tasks using a Genetic Algorithm (GA) for feature selection. However, GAs suffer from poor modeling of parameter correlations and require extensive hyperparameter tuning. This thesis proposes extending the Gen-SPP by replacing the GAs with the Covariance Matrix Adaptation Evolution Strategy (CMA-ES), a more robust, distribution-based optimization algorithm. CMA-ES adaptively models parameter dependencies during search, enabling a more effective exploration of the search space. Our experiments on benchmark datasets demonstrate that CMA-ES can improve both classification accuracy and rationale fidelity compared to the GA baseline. Although CMA-ES demands higher computational memory, it can offer a stronger optimization strategy for explainable AI systems.

Abstract
Tipologia del documento
Tesi di laurea (Laurea magistrale)
Autore della tesi
Clotan, Paul Ioan
Relatore della tesi
Correlatore della tesi
Scuola
Corso di studio
Ordinamento Cds
DM270
Parole chiave
Explainable Artificial Intelligence (XAI), Selective Rationalization, Gen-SPP Framework, Covariance Matrix Adaptation Evolution Strategy (CMA-ES), Genetic Algorithms (GA), Neuro-symbolic Optimization, Sparse Rationale Generation, Model Interpretability, Text Classification, Deep Learning
Data di discussione della Tesi
22 Luglio 2025
URI

Altri metadati

Gestione del documento: Visualizza il documento

^