| Titre : |
Exploring a new method for the formal verification of neural networks through coloured petri net modeling |
| Type de document : |
document électronique |
| Auteurs : |
Bochra Lafifi, Auteur ; Oussama Arki, Directeur de thèse ; Asma Gabis, Directeur de thèse ; Kais Klai, Directeur de thèse ; Faten Chakchouk, Directeur de thèse |
| Editeur : |
[S.l.] : [s.n.] |
| Année de publication : |
2025 |
| Importance : |
1 fichier PDF (5 Mo) |
| Présentation : |
ill. |
| Note générale : |
Mode d'accès : accès au texte intégral par intranet.
Mémoire de Projet de Fin d’Études : Génie Industriel.Date Science et intelligence artificiel : Alger, École Nationale Polytechnique : 2025
Bibliogr. p. 85 - 89 .- Annexe p. 90 - 96 |
| Langues : |
Anglais (eng) |
| Mots-clés : |
Colored Petri Nets
Neural Networks
Formal Verification
Explainable Artificial
Intelligence (XAI)
Model Checking |
| Index. décimale : |
PI00625 |
| Résumé : |
This thesis introduces the Colored Petri Neural Network (CPNN), a novel frame- work that integrates Colored Petri Nets (CPNs) with multi-layer perceptrons (MLPs) to enhance the interpretability of neural networks. The CPNN model addresses the challenge of explainability in deep learning by enabling formal, fine-grained tracking of information flow during forward propagation. This approach provides transparent insights into feature contributions and decision-making processes.
By leveraging the formal verification strengths of CPNs, the model supports rigorous analysis without compromising predictive performance—particularly in critical domains such as healthcare. Additionally, a mathematical investigation of the neural network hyperparameters effects on state space complexity reveals the influence of factors like layer depth and mini-batch size on computational requirements, guiding more efficient design and verification.
This work lays the foundation for developing interpretable, efficient, and verifiable deep learning systems in critical applications. |
Exploring a new method for the formal verification of neural networks through coloured petri net modeling [document électronique] / Bochra Lafifi, Auteur ; Oussama Arki, Directeur de thèse ; Asma Gabis, Directeur de thèse ; Kais Klai, Directeur de thèse ; Faten Chakchouk, Directeur de thèse . - [S.l.] : [s.n.], 2025 . - 1 fichier PDF (5 Mo) : ill. Mode d'accès : accès au texte intégral par intranet.
Mémoire de Projet de Fin d’Études : Génie Industriel.Date Science et intelligence artificiel : Alger, École Nationale Polytechnique : 2025
Bibliogr. p. 85 - 89 .- Annexe p. 90 - 96 Langues : Anglais ( eng)
| Mots-clés : |
Colored Petri Nets
Neural Networks
Formal Verification
Explainable Artificial
Intelligence (XAI)
Model Checking |
| Index. décimale : |
PI00625 |
| Résumé : |
This thesis introduces the Colored Petri Neural Network (CPNN), a novel frame- work that integrates Colored Petri Nets (CPNs) with multi-layer perceptrons (MLPs) to enhance the interpretability of neural networks. The CPNN model addresses the challenge of explainability in deep learning by enabling formal, fine-grained tracking of information flow during forward propagation. This approach provides transparent insights into feature contributions and decision-making processes.
By leveraging the formal verification strengths of CPNs, the model supports rigorous analysis without compromising predictive performance—particularly in critical domains such as healthcare. Additionally, a mathematical investigation of the neural network hyperparameters effects on state space complexity reveals the influence of factors like layer depth and mini-batch size on computational requirements, guiding more efficient design and verification.
This work lays the foundation for developing interpretable, efficient, and verifiable deep learning systems in critical applications. |
|
Ajouter le résultat dans votre panier Faire une suggestion Affiner la rechercheExploring a new method for the formal verification of neural networks through coloured petri net modeling (2025)
