When to trust AI: advances and challenges for certification of neural networks

M Kwiatkowska, X Zhang - 2023 18th Conference on Computer …, 2023 - ieeexplore.ieee.org
Artificial intelligence (AI) has been advancing at a fast pace and it is now poised for
deployment in a wide range of applications, such as autonomous systems, medical …

Certified quantization strategy synthesis for neural networks

Y Zhang, G Chen, F Song, J Sun, JS Dong - International Symposium on …, 2024 - Springer
Quantization plays an important role in deploying neural networks on embedded, real-time
systems with limited computing and storage resources (eg, edge devices). It significantly …

A Unified Framework for Probabilistic Verification of AI Systems via Weighted Model Integration

P Morettin, A Passerini, R Sebastiani - arxiv preprint arxiv:2402.04892, 2024 - arxiv.org
The probabilistic formal verification (PFV) of AI systems is in its infancy. So far, approaches
have been limited to ad-hoc algorithms for specific classes of models and/or properties. We …

Tractable probabilistic models for causal learning and reasoning

B Wang - 2023 - ora.ox.ac.uk
This thesis examines the application of tractable probabilistic modelling principles to causal
learning and reasoning. Tractable probabilistic modelling is a promising paradigm that has …