Page Not Found
Page not found. Your pixels are in another canvas.
Sitemap
A list of all the posts and pages found on the site. For you robots out there is an XML version available for digesting as well.
Pages
Théophile Sautory
Machine learning engineer focused on evaluation, robustness, and real-world deployment.
Page not in menu
This is a page not in th emain menu
Posts
portfolio
publications
International Journal of Computational Fluid Dynamics, 2020
A Priori Sub-grid Modelling Using Artificial Neural Networks
This paper concerns the use of artificial neural networks to close the turbulence model in Large Eddy Simulations. You can find more information on the project by clicking on the paper title above, or reading the paper below.
Thirty- Fifth AAAI Conference on Artificial Intelligence Workshop on Hybrid Artificial Intelligence, 2021
HySTER: A Hybrid Spatio-Temporal Event Reasoner
This paper presents a novel neuro-symbolic appraoch to video question answering, performing perception tasks with deep learning and temporal and causal reasoning with inductive logic programming. You can find more information on the project by clicking on the paper title above, or reading the paper below.
SPIE Optical Metrology. Proceedings Volume 11787, Automated Visual Inspection and Machine Vision IV, 2021
Data augmentation and pre-trained networks for extremely low data regimes unsupervised visual inspection
This paper studies the robustness of using deep features from pre-trained networks on low data regimes anomaly detection tasks.
International Conference on Logic Programming and Nonmonotonic Reasoning, 2022
Learning to Rank the Distinctiveness of Behaviour in Serial Offending
This paper presents the first learning based approach aimed at identifying contexts within which behaviour may be considered distinctive in the context of comparative case analysis used to detect serial offending.
arXiv preprint, 2024
Reinforcement Learning from LLM Feedback to Counteract Goal Misgeneralization
We introduce a method to address goal misgeneralization in reinforcement learning by using LLM feedback to build a reward model that improves generalization.
arXiv preprint, 2024
Utilitarian Beliefs in Social Networks: Explaining the Emergence of Hatred
We study how utilitarian beliefs evolve in social networks and how they can lead to the emergence of hatred.
Journal of Biomechanical Engineering, 2024
Unsupervised Denoising and Super-Resolution of Vascular Flow Data by Physics-Informed Machine Learning
We present a physics-informed machine learning approach for unsupervised denoising and super-resolution of vascular flow data.