6 papers
Training LayoutLM from Scratch for Efficient Named-Entity Recognition in the Insurance Domain
Benno Uthayasooriyar, Antoine Ly, Franck Vermet +1
Generic pre-trained neural networks may struggle to produce good results in specialized domains like finance and insurance. This is due to a domain mismatch between training data a…
Diffusion Posterior Sampling for Synergistic Reconstruction in Spectral Computed Tomography
Corentin Vazia, Alexandre Bousse, Béatrice Vedel +6
Using recent advances in generative artificial intelligence (AI) brought by diffusion models, this paper introduces a new synergistic method for spectral computed tomography (CT) r…
Model Transparency and Interpretability : Survey and Application to the Insurance Industry
Dimitri Delcaillau, Antoine Ly, Alize Papp +1
The use of models, even if efficient, must be accompanied by an understanding at all levels of the process that transforms data (upstream and downstream). Thus, needs increase to d…
On the capacity of a new model of associative memory based on neural cliques
Judith Heusel, Matthias Löwe, Franck Vermet
Based on recent work by Gripon and Berrou, we introduce a new model of an associative memory. We show that this model has an efficiency bounded away from 0 and is therefore signifi…
Large deviation upper bounds for sums of positively associated indicators
Matthias Löwe, Franck Vermet
We give exponential upper bounds for , in particular , where is a sum of indicator random variables that are positively associated. These bounds allow, in p…
Mixing times for the Swapping Algorithm on the Blume-Emery-Griffiths Model
M. Ebbers, H. Knöpfel, M. Löwe +1
We analyze the so called Swapping Algorithm, a parallel version of the well-known Metropolis-Hastings algorithm, on the mean-field version of the Blume-Emery-Griffiths model in sta…