• Table of contents
• Wiki of the Machine Learning / Deep Learning Pole
  • Reference publications
  • Books & Code Examples
  • Frameworks to start & to document in ML/DL
  • Online courses
  • Next conferences or training workshops
  • Previous conferences with astrophysical topics
  • Previous conferences / training workshops
  • ML/DL pole Seminars
  • ML/DL pole Staff & Projects
  • Available GPUs computing resources for LAM staff

Wiki of the Machine Learning / Deep Learning Pole¶

INFORMATION WEB PAGE for the ML/DL Pole at CeSAM
This is a selection of some references that may be useful to start or consolidate your knowledge. This information is of course not exhaustive and any suggestions for additions are welcome. If you have any questions, please send an email to morgan.gray@lam.fr

Reference publications¶

• General comments on :
  • Machine Learning : Baron(19) MLinAstronomyOverview & Mehta MLforPhysicists
  • A glossary that defines general ML terms : https://developers.google.com/machine-learning/glossary#a
  • Deep Learning : Hadji(18) CNN-Overview
• Some classical Neural Network architectures :
  • Simonyan VGGNet - He(15) ResNet - He(16) ResNet
  • Szegedy(14) Inception - Szegedy(15) RethinkingInception - Szegedy(16) InceptionV4 InceptionResNet - Chollet Xception
  • Makhzani AdversarialAutoencoders - Goodfellow GenerativeAdversarialNets
• Practical advice (methodology, specific aspects) :
  • Bengio(12) PracticalRecommendations - Smith(18) Hyperparameters - OptimizerAlgorithms - Dropout - BatchNormalization

Books & Code Examples¶

• Hands-On Machine Learning with Scikit-Learn, Keras & Tensorflow by Aurélien Géron (O'Reilley editor, third edition)
  • Jupyter notebooks for the code samples : https://github.com/ageron/handson-ml3
• Deep Learning with Python by François Chollet (Manning editor) : a good presentation of Keras to make Deep Learning
  • Jupyter notebooks for the code samples : https://github.com/fchollet/deep-learning-with-python-notebooks
  • Examples of codes with several issues & neural networks : https://keras.io/examples/ ; https://keras.io/api/applications/
• Deep Learning by Goodfellow, Bengio, Courville (MIT press book editor) : a more theoretical book
  • free access per chapter : https://www.deeplearningbook.org/
• Probabilistic Deep Learning with Python, Keras and Tensorflow Probability by Durr, Sic, Murina (Manning editor)
• Bayesians methods for hackers, Probabilistic Programming and Bayesian Inference by Cameron Davidson-Pilon (Addison-Wesley Data & Analytics editor)
  • free access per chapter : https://camdavidsonpilon.github.io/Probabilistic-Programming-and-Bayesian-Methods-for-Hackers/
• Pattern Recognition & Machine Learning by Christopher M. Bishop (Springer Editor)
  • free to download : http://mng.bz/oPWZ
• Statistics, Data Mining and Machine Learning in Astronomy by Ivezic, Connolly, Vanderplas & Gray (Princeton Press)
  • HTML documentation : https://www.astroml.org/ ; Source-code repository: https://github.com/astroML/astroML
• The Elements of Statistical Learning by Hastie, Tibshirani & Friedmman (Springer Editor)
  • free to download : https://web.stanford.edu/~hastie/ElemStatLearn/
• Last, but not least : https://github.com/ChristosChristofidis/awesome-deep-learning?tab=readme-ov-file#books

Frameworks to start & to document in ML/DL¶

• ScikitLearn : https://scikit-learn.org/stable/user_guide.html
• Keras : https://keras.io/getting_started/ ; https://keras.io/api/ ; https://keras.io/guides/
• Tensorflow : https://www.tensorflow.org/api_docs/python/tf
• Pytorch : https://pytorch.org/get-started/locally/ ; https://pytorch.org/tutorials/
• A platform for the Machine Learning lifecycle : https://mlflow.org/
• ONNX : https://onnx.ai/get-started.html
• News and best papers proposed by the IDRIS YouTube chanel : https://www.youtube.com/@idriscnrs/videos
• Last, but not least : https://github.com/ChristosChristofidis/awesome-deep-learning?tab=readme-ov-file#frameworks

Online courses¶

• FIDLE 24/25 (in French) : Introduction au Deep Learning (un très bon cours !)
  • Programme : https://fidle.cnrs.fr/w3/programme.html
  • Videos : https://www.youtube.com/@CNRS-FIDLE/videos
  • Notebooks : https://fidle.cnrs.fr/done/
  • Supports : https://gricad-gitlab.univ-grenoble-alpes.fr/talks/fidle
• JRES 2022 (in French) : Le Deep Learning en 100 minutes !
  • https://replay.jres.org/w/kzX7FHoPJSazgfxrJEwMWK
• CNAM (in French) :
  • Réseaux de neurones : slides Formation CNAM ; videos : send an email request
  • Modélisation descriptive et introduction aux réseaux de neurones http://cedric.cnam.fr/vertigo/Cours/ml/
  • Modélisation décisionnelle et apprentissage profond http://cedric.cnam.fr/vertigo/Cours/ml2/
• STANFORD University (in English) :
  • Machine Learning : https://www.coursera.org/learn/machine-learning#syllabus ; slides Formation COURSERA
  • CNN for Visual Recognition : https://cs231n.github.io/
• ML/DL Mastery (in English) : https://machinelearningmastery.com/start-here/
• Last, but not least : https://github.com/ChristosChristofidis/awesome-deep-learning?tab=readme-ov-file#courses

Next conferences or training workshops¶

Previous conferences with astrophysical topics¶

• IAP2023, Debating the Potential of Machine Learning in astronomical surveys : https://indico.iap.fr/event/1/timetable/#20231127.detailed
• CNRS School 2023, AstroInformatics Thematic School : https://astroinfo2023.sciencesconf.org/
• ASNUM2002, Journées de l'Action Spécifique Numérique Astrophysique : https://asnum2022.sciencesconf.org/ (videos)
• LISA data analysis, From classical methods to Machine Learning : https://indico.in2p3.fr/event/27706/program (for the slides & videos, send an email request)
• Bayesian Deep Learning for Cosmology & Time Domain Astrophysics : https://astrodeep.net/workshop2022/ (videos)
• ESO/ESA SciOps workshop on Artificial Intelligence for Science and Operations in Astronomy : https://www.eso.org/sci/meetings/2022/SCIOPS2022/program.html (only slides)
• Ecole CNRS 2021 (in French), Ecole Thématique AstroInformatique : https://astroinfo2021.sciencesconf.org/program
• Debating the potential of ML in astronomical surveys, IAP2021 : https://ml-iap2021.sciencesconf.org/browse/session (videos)
• Ecole CNRS 2020 (in French) : ANF Machine Learning pour Informaticiens, bases et enjeux du Machine Learning et du Deep Learning : https://gitlab.in2p3.fr/ri3/ecole-info/2020/anf-machine-learning/-/tree/master/notebooks
• Bayesian Deep Learning for Cosmology & Gravitational waves : https://astrodeep.net/workshop2020/#schedule (videos)

Previous conferences / training workshops¶

• Forum Orap 2024 (in French) HPC et simulation à l'heure de l'IA : défis et opportunités :
  • slides & videos : https://orap.irisa.fr/forum-30-ans/
• Colloque MITI 2024 (in French) Jumeaux numériques, nouvelles frontières :
  • videos : https://miti.cnrs.fr/wp-content/uploads/2024/04/Colloque_jumeaux_numerique_programme_interactif.pdf
• CIRM 2021 (in English) : Mathematics, Signal Processing and Learning ​ (more theoretical courses with a mathematical view & practical sessions)
  • https://conferences.cirm-math.fr/2472.html
  • slides : https://www.i2m.univ-amu.fr/seminaires_signal_apprentissage/Conf/Jan2021/index.php
  • videos : https://library.cirm-math.fr/ListRecord.htm?list=request&table=3&NumReq=115&cluster_1=2472
• JDEV 2020 (in French) :
  • Python, préparation des données avec Panda & Apprentissage Automatique avec Scikitlearn : http://devlog.cnrs.fr/jdev2020/t8.a05
    supports : https://gitlab.in2p3.fr/aboucaud/atelier-jdev-2020
  • Fondamentaux Apprentissage Automatique avec Python & ScikitLearn : http://devlog.cnrs.fr/jdev2017/t8.a04
    supports : http://laurent.risser.free.fr/TMP_SHARE/JDEV2020/
  • Introduction Keras & Tensorflow : http://devlog.cnrs.fr/jdev2020/t8.ap04
    supports : https://gricad-gitlab.univ-grenoble-alpes.fr/talks/fidle/
  • Introduction Deep Learning & PyTorch : http://devlog.cnrs.fr/jdev2020/t8.ap01
    supports : http://laurent.risser.free.fr/TMP_SHARE/JDEV2020_T8_AP01/
  • Programmer et déployer votre IA (objectifs et vidéos http://devlog.cnrs.fr/jdev2020/t8)

ML/DL pole Seminars¶

For the presentations, the slides can be retrieved with the link; the videos can be viewed on https://seminars.lam.fr/#MLDL

• 26/11/2024 : Marc Huertas-Company " Deep Learning the physics of galaxy formation "
• 23/09/2024 : Loris Berthelot (LIS/LAM) " Towards an unbiased detection of Galactic filaments using innovative Deep Learning methods " (240923 Berthelot)
• 01/07/2024 : Maxime Dumont (LAM/ONERA) " Physics Informed Neural Network & VAE for phasing space segmented telescope " (240701 Dumont)
• 15/04/2024 : Camille Godbillot (CEREGE) " Towards the use of CNNs to constrain the phytoplankton community response to environmental changes: an example from the Mediterranean Sea " (240415 Godbillot)
• 11/03/2024 : Hugo Vivien (LAM) " Panopticon, Detecting transits in PLATO lightcurves " (240311 Vivien)
• 08/01/2024 : Adeline Paiement (LIS) " Physics-informed Deep Neural Network for characterising galaxy morphology " (240108 Paiement)
• 04/12/2023 : Reda Ait Ouhamed (LAM) " Galaxy redsfhit estimation from multi-band images with Deep Learning " (231204 Reda)
• 20/11/2023 : Raoul Canameras (MPA-Garching) " Supervised Deep Learning methods for Rubin LSST, lmage classification, mass modeling and photometric redshift prediction " (231120 Canameras)
• 05/04/2023 : Eric Wulff (CERN) " Hyperparameter Optimization for DL using HPC" (230405 Wulff)
• 24/11/2022 : Maxime Quesnel (University of Liège) " A Simulator-based Autoencoder approach for Focal-Plane Wavefront Sensing" (221124 Quesnel)
• 25/03/2022 : François Lanusse (CosmoStat) " Probabilistic Deep Learning for Weak Lensing : from Mass-Mapping to Cosmological Parameter Inference " (https://eiffl.github.io/LAM2022/)
• 04/05/2021 : Raoul Canameras (MPA-Garching) " Finding and modeling strong gravitational lenses with deep neural networks " (210504 Canameras)
• 30/03/2021 : Alexandre Boucaud & Hubert Bretonnière (LAC) " FlowVAE: taking control of galaxy image simulations with deep generative networks "
• 09/03/2021 : Laurent Risser (IMT) " Explainability techniques for black-box decision rules in Machine Learning " (210309 Risser)
• 11/02/2021 : Sidonie Lefebvre (ONERA/DOTA) " Generative Adversarial Networks (GANs) : concept and application to cloudy sky images synthesis " (210211 Lefevbre)
• 01/02/2021 : Nicolas Audebert (CNAM) " Hyperspectral remote sensing data analysis using Deep Learning " (210201 Audebert)
• 18/01/2021 : François-Xavier Dupé (LIS) " How Machine Learning can help to automate processing tasks ? An example with image denoising " (210118 Dupe)
• 11/01/2021 : Julien Wojak (Institut Fresnel) " Deep Learning : focus on auto-encoder as a pre-processing step for classification " (210111 Wojak)

ML/DL pole Staff & Projects¶

• Staff (FTE) : Morgan Gray (100%) ; Jean-Charles Meunier (75%) ; Raoul Canameras (100%) ; Lucas Barbier (40%)
• Projects :
  • ANR APPLY (GRD): https://sites.google.com/view/anr-apply/home ; Deep Learning for PSF estimation GRAY(22) DeepLoop
  • EUCLID (ESA) : https://sci.esa.int/web/euclid/-/science ; https://www.euclid-ec.org/public/data/ground-segment/
  • AZIMOV (GRD/ONERA): Phasing Segmented Telescopes with Deep Learning Dumont(24) PhasingSegmentedTelescopes DL
  • BigSF (GECO/LIS): Supervised Machine Learning on Galactic filaments https://arxiv.org/abs/2212.00463 ; Berthelot(24) Supervised ML GalacticFilaments
  • ISOS (GRD/France2020): Reinforcement Learning for PAPYRUS Camelo(23) AO4ELT7 ; Camelo(24) SPIE
  • PETALING (GRD/France2020): Estimating the ELT’s Differential Pistons with Deep Learning Chauvet(23) AO4ELT7 ; Janin(24) SPIE-Petaling
  • DOSSA (GRD/Unistellar/Spaceable/France2030): Janin(24) SPIE-SpaceSurveillance
• Poster of the ML/DL pole at the LAM/ONERA/FRESNEL day (16/06/2022): Gray PosterPoleMLDL-A4
• Presentation of the ML/DL pole at the OSU-AI scientific day (20/04/2022): Gray JourneeIA-OSU
• Presentation of the ML/DL pole to the LAM scientific council : CeSAM__2020-v3.pdf
• Proposal for the creation of the ML/DL pole : Visioconférence du 09/10/2020

Available GPUs computing resources for LAM staff¶

• GPU partition on the LAM cluster (responsible JC Lambert) : 7 GPUs RTX2080 + 11 GPUs A40
  https://projets.lam.fr/projects/cluster-de-calcul-du-lam/wiki#GPU-partition
• Aix-Marseille University Mesocentre cluster : several GPU partitions (volta partition : 20 GPUs V100)
  https://mesocentre.univ-amu.fr/appel-a-projets/
  https://mesocentre.univ-amu.fr/les-tutoriaux/
  https://mesocentre.univ-amu.fr/copernicus/login.html
• MESONET, in which AMU is a partner, aims to deploy a set of HPC resources accessible to all academic users working in France : https://www.mesonet.fr/