Notes and Comments on S. Mallat’s Lectures at Collège de France (2018) - Archive ouverte HAL Accéder directement au contenu
Cours Année : 2018

Notes and Comments on S. Mallat’s Lectures at Collège de France (2018)

Résumé

The 2018 course by Stéphane Mallat, Professor at the Collège de France, focuses on the challenge of high-dimensional data, particularly in the face of the curse of dimensionality. It reviews Fourier Analysis, followed by Wavelet Analysis, and regression/classification tasks using kernels, before delving into neural networks. Gradient descent optimization is described along with its convergence properties. What sets this course apart is its mathematical perspective on 'Why does it work?' or 'What are the underlying information and structures for it to work?' This distinguishes it from courses on how to implement specific methods using certain libraries or code.
Fichier principal
Vignette du fichier
Resume-2018_EN.pdf (1.55 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04550709 , version 1 (18-04-2024)

Licence

Paternité - Pas d'utilisation commerciale - Pas de modification

Identifiants

  • HAL Id : hal-04550709 , version 1

Citer

Jean-Eric Campagne. Notes and Comments on S. Mallat’s Lectures at Collège de France (2018): The challenge of learning in the face of the curse of high dimensionality. Master. The learning process in the face of the curse of high dimensionality, https://www.college-de-france.fr/fr/agenda/cours/apprentissage-face-la-malediction-de-la-grande-dimension, France. 2018, pp.108. ⟨hal-04550709⟩
0 Consultations
1 Téléchargements

Partager

Gmail Facebook X LinkedIn More