Fundamentals of Machine Learning with Python - Advanced Level À distance
Dernière mise à jour : 30/10/2026
Unité de recherche
Description
Part 1 - Convolutional neural networks:
- The notion of invariance and how to cope with it
- Data augmentation
- Classical deep architecture - the example of Resnet18
Part 2 - Transformers and Learning on sequential data:
- Auto-regressive models
- The notions of transformers and attention
- Text data: Tokenizers and how to use them
Part 3 - ML pipeline and Model Fine-tuning:
- Efficient baseline models: Random Forest, XGBoost
- Hyperparameter tuning with optuna
- Few shot learning, domain adaptation
- Example on images and/or text
- Finetuning with Low Rank Adaptation (LoRA)
Part 4 - Time series:
- Dynamic Time Warping
- Specific crossvalidation and evaluation procedures
- Clustering time series
- Dictionary learning
Part 5 - Physics-informed Neural Networks:
- Physics-informed loss
- Neural Operators
- Examples on ODEs, PDEs and data assimilation
Part 6 – Generative methods
- Unconditional, class-conditional, and embedding-conditional generative models
- Foundational techniques like normalizing flows
- Diffusion models and flow matching
- Text-to-image models such as Stable Diffusion or DALL·E
The learning of these concepts will be illustrated and put into practice through the handling of the scikit-learn and PyTorch libraries throughout the training.
Objectifs de la formation
- For a knowledgeable audience in Machine Learning, introduction and further exploration of some modern artificial intelligence methods
- Implementation of Deep Learning methodologies (and others) on various types of data
- Use of development frameworks such as scikit-learn and PyTorch
Public visé
Researchers, engineers and data scientists
Prérequis
Solid knowledge of scientific Python (manipulation of data tables with numpy and/or pandas, class concepts). Generalist knowledge in linear algebra and statistics.
Modalités pédagogiques
Lectures based on interactive Jupyter notebooks, application exercises.
Moyens et supports pédagogiques
A file in PDF format will be given to the trainees at the end of the training.
Modalités d'évaluation et de suivi
Throughout the training, corrected exercises and interactive quizzes will allow the trainee to evaluate the acquisition of knowledge. A certificate of completion is issued at the end of the training.
Formateurs
Informations sur l'admission
Admission to this training course does not involve any prior assessment, test or selection process. Registration is confirmed once the completed application has been received and confirmed by the training provider.
Modalités tarifaires spécifiques
All our training courses are VAT exempt. Enjoy exclusive volume discounts: save 5% when registering 3-4 participants, 10% for 5-6, and 20% for groups of 7 or more. CNRS employees benefit from a special 20% discount.
Informations sur l'accessibilité
Our organisation is committed to ensuring inclusive and equitable access to its training programmes, whether delivered online or in person, for all participants, including people with disabilities. A dedicated accessibility contact is available to assess individual needs and, where possible, implement appropriate pedagogical, technical and organisational adjustments.