Quantification of Neural Networks on Fixed-Point Architectures with Formal Guarantees
Talk, Défi Embarquabilité de l’IA@ANITI, ENAC
Recent/Upcoming Talks
Formal Methods for Frugal Computing in Numerical Software
Talk, Invited Talk @Department of Informatics, Universitas Diponegoro, Indonesia
Towards Bit-Level Dominance Preserving Quantization of Neural Classifiers
Talk, SOAP@PLDI 2025, Seoul, Republic of Korea
Efficient Implementation of Neural Networks Usual Layers on Fixed-Point Architectures
Talk, Journées Formalisation des Activités Concurrentes (FAC 2025), France
Quantization of DNNs: Challenges and Opportunities
Talk, CAFEIN Workshop (Combinaison d'Approches Formelles pour l'Étude d'INvariants numériques), France
Rigorous Floating-Point to Fixed-Point Quantization of Deep Neural Networks on STM32 Micro-controllers
Talk, 10th International Conference on Control, Decision and Information Technologies (CoDIT 2024), Valletta, Malta
Compile-Time Optimization of the Energy Consumption of Numerical Computations
Talk, ACM International Conference on Computing Frontiers (CF 2024), Ischia, Italy