8–12 juil. 2024
BÂTIMENT D’ENSEIGNEMENT MUTUALISÉ (BEM)
Fuseau horaire Europe/Paris

Session

Machine Learning for Science School

8 juil. 2024, 09:30
BÂTIMENT D’ENSEIGNEMENT MUTUALISÉ (BEM)

BÂTIMENT D’ENSEIGNEMENT MUTUALISÉ (BEM)

Bâtiment d'Enseignement Mutualisé (BEM) Av. Fresnel, 91120 Palaiseau

Description

Goal: Introduce the basics of ML and describe in details how to perform validation

  • History and terminology
  • Problem setup for ML basics (Model, loss, learning procedure, features)
  • Generalization in ML (overfitting, underfitting and model selection)
  • Validation (performance metrics, validation strategies, statistical analysis)

Documents de présentation

Aucun document.

  1. Olivier Colliot
    08/07/2024 09:30

    Goal: Introduce the basics of ML and describe in details how to perform validation

    • History and terminology
    • Problem setup for ML basics (Model, loss, learning procedure, features)
    • Generalization in ML (overfitting, underfitting and model selection)
    • Validation (performance metrics, validation strategies, statistical analysis)
    Aller à la page de la contribution
  2. Guillaume Lemaitre
    08/07/2024 14:00

    Goal: Introduce the scikit-learn API, with a focus on practical insights on the model validation and selection.

    - Overview of a simple cross-validation scheme k-fold
    - Overview of metrics (Regression, Classification)
    - Model selection through SearchCV
    - Cross validation in complex settings (stratification, groups, non-iid data)
    
    Aller à la page de la contribution
  3. Thomas Moreau (Inria)
    09/07/2024 09:30

    Goal: Introduce the different types of data, with a focus on time-series, and the different methodologies to apply on each type.

    - Overview of the different types of data: tabular data, time series, images, graph, signals.
    - Overview of the specific problems and jargon with time series and signals.
    - How to get back to a “classical” ML framework?
    - Practical illustrations...
    
    Aller à la page de la contribution
  4. Romain Ménégaux
    09/07/2024 14:00

    Goal: Describe the main types of deep learning architectures, and apply them to a concrete example from life sciences.

    - Introduction: what is deep learning and why is everyone doing it?
    - Overview of the main types of deep learning architectures: MLP, convolutional, and transformers. When to use one or the other?
    - Overview of the different training and regularization...
    
    Aller à la page de la contribution
Ordre du jour en construction...