Colloque - David Ryckelynck : Self Supervised Machine Learning of ROM-nets for Mechanics of Materials
Épisode de Colloques du Collège de France - Collège de France par Collège de France · 24 juin 2026 · 39 min
Yvon Maday
Chaire Informatique et sciences numériques
Collège de France
Année 2025-2026
Colloque : Aspects mathématiques et appliqués des méthodes de réduction de complexité - David Ryckelynck : Self Supervised Machine Learning of ROM-nets for Mechanics of Materials
David Ryckelynck
Professeur à Mines Paris – PSL
Résumé
We propose a general framework for projection-based model order reduction using self-supervised machine learning [1]. For parametric elliptic equations this approach is theoretically based on Céa's Lemma. The proposed methodology, called ROM-net [2], consists in using deep learning techniques to adapt the reduced-order model to a stochastic input tensor whose nonparametrized variabilities strongly influence the quantities of interest for a given physics problem. In particular, we introduce the concept of dictionary-based ROM-nets, where deep neural networks recommend a suitable local reduced-order model from a dictionary. The dictionary of local reduced-order models is constructed from a clustering of vector subspaces in a Grassmann manifold.
It enables the identification of the local low-dimensional subspace in which the solutions evolve for different input tensors. This methodology is applied to an anisothermal elastoplastic problem in structural mechanics coupled to a stochastic thermal field. When using deep neural networks, the selection of the best reduced-order model for a given thermal loading is 60 times faster than when following the clustering procedure used in the training phase. The implementation of local hyper-reduction schemes using a dictionary-based ROM-net is straightforward. The extension to variational inequalities will be addressed at the end of the lecture.
Autres épisodes de « Colloques du Collège de France - Collège de France »
- Colloque - Karen E. Willcox : Multifidelity Proper Orthogonal Decomposition 24 juin 2026
- Colloque - Tommaso Taddei : Registration in Bounded Domains for Model Reduction of Parametric Conservation Laws 24 juin 2026
- Colloque - Élise Grosjean : A Doubly Reduced Approximation for the Solution to PDEs Based on a Domain Truncation and a Reduced Basis Method: Application to Navier-Stokes Equations 24 juin 2026
- Colloque - Kathrin Smetana : Certified Randomized Model Order Reduction Methods for High-Dimensional Approximation 24 juin 2026
- Colloque - Geneviève Dusson : Metric-Based Nonlinear Model Order Reduction with Applications to Quantum Chemistry 24 juin 2026
- Colloque - Anthony Nouy : Stable Nonlinear Manifold Approximation Using Compositional Networks 24 juin 2026
- Colloque - Ludovic Chamoin : Integrated Structural Health Monitoring with Real-time Data Assimilation and Hybrid Twins 23 juin 2026
- Colloque - Evie Nielen : Efficient Greedy Sampling for Model Order Reduction 23 juin 2026
- Colloque - Clémentine Prieur : Diffeomorphism-Based Feature Learning Using Poincaré Inequalities 23 juin 2026
- Colloque - Benjamin Peherstorfer : Dirac-Frenkel Dynamics with Momentum 23 juin 2026
- Colloque - Andrea Manzoni : Reduced Order Modeling and Scientific Machine Learning: Synergies and Opportunities 23 juin 2026
- Colloque - Albert Cohen : Optimal Linear and Non-Linear Dimensionality Reduction 23 juin 2026
- Colloque - Mario Ohlberger : Reduced Order Surrogate Models for PDE-Constrained Optimization and Inverse Problems 22 juin 2026
- Colloque - Beatriz Moya : Avancées en modélisation hybride : vers la transition numérique des territoires 22 juin 2026
- Colloque - Jörg Fehr : From Latent Space Representations to Practical Surrogate Models for Structural Dynamical Systems 22 juin 2026
À propos du podcast
Colloques interdisciplinaires du Collège de France Événements de la vie scientifique de l'établissement, les colloques, dont le programme comprend à la fois des professeurs du Collège de France et des conférenciers invités, traite de thèmes aux nombreuses ramifications, dont les enjeux…
Épisodes similaires
- 2026-04 V2 PINS.mp4 – Lille.Pod
- BONUS _ 7 CHOSES A SAVOIR SUR L'ARGENT POUR (ENFIN) DEVENIR RICHE – FINI LES DETTES !
- Episode #16 Jordan Marion - L'école d'astrologie – Pour l’Amour du Ciel
- E116 - Why You Understand French but Can't Speak It – Intermediate French Podcast - Ta vie en français
- La guillotine : un progrès social ? # Révolution française 🇫🇷 DELF A2 / B1 - French intermediate level - Compréhension orale – Escargot - News & Culture in Simple French
- André Malraux – La base
Tous les épisodes de Colloques du Collège de France - Collège de France · Plus de podcasts Éducation