PostDoc position on deep learning accelerated multiscale modeling of flows H/F at IMT Nord Europe

·         Improving the generalization capabilities by estimating the prediction error and carefully designing the training dataset, for instance using active learning [2] or self-supervised learning [3,4],

·         Ensuring the convexity of the neural network prediction with respect to the input data [5,6].

Within this project involving two research centers of IMT Nord Europe as well as a research group of the National University of Singapore, the postdoctoral fellow will focus on accelerating calculations with deep learning. The postdoctoral fellow will develop a deep learning model that will be integrated in a multiscale finite element code developed by other partners of the MISSA project. Challenging applications to real manufacturing processes will be addressed.

The postdoctoral research will be supervised by Prof. Shakoor, Itier and Mennesson from IMT Nord Europe. Participation in teaching activities is possible up to a limit of 64 hours per school year for postdocs who wish to pursue a career in academia. This position offers:

·         A high-level and exciting international research environment in a renowned institution

·         Being part of an international project team with contacts worldwide

·         A thorough scientific education and training on deep learning and its application to fluid mechanics

·         The possibility to participate in local as well as international workshops and conferences

REFERENCES:
[1] K. Shinde et al., Dimensionality reduction through convolutional autoencoders for fracture patterns prediction, Applied Mathematical Modelling, 114:94-113, 2023
[2] Y. Gal et al., Deep bayesian active learning with image data, Proceedings of the 34th International Conference on Machine Learning, 70:1183-1192, 2017
[3] M. Caron et al., Emerging properties in self-supervised vision transformers, Proceedings of the IEEE/CVF International Conference on Computer Vision, 9650-9660, 2021
[4] T. Chen et al., A Simple Framework for Contrastive Learning of Visual Representations, Proceedings of the 37th International Conference on Machine Learning, 119:1597-1607, 2020
[5] M. Ławryńczuk, Input convex neural networks in nonlinear predictive control: A multi-model approach, Neurocomputing, 513:273-293, 2022
[6] O. Aslan et al., Convex deep learning via normalized kernels, Advances in Neural Information [...]