Catégorie
Event

SAVE THE DATE! DATAIA Seminar - "Nonlinear independent component analysis" - Aapo Hyvärinen

Bandeau image

SAVE THE DATE! DATAIA Seminar - "Nonlinear independent component analysis" - Aapo Hyvärinen

  • News on the same topic
Chapo
"Nonlinear independent component analysis: A principled framework for unsupervised deep learning"
Aapo Hyvärinen leads DATAIA Seminar
Contenu
Corps de texte

Aapo Hyvärinen (Inria, University of Helsinki) is the speaker of the DATAIA’s seminar of the 9th October that will focus on one of the deepest challenges in machine learning: unsupervised learning.

He will illustrate and discuss the nonlinear Independent Component Analysis (ICA), the method that overcomes this problem; his contributions to the topic; and the connection between nonlinear ICA and Variational AutoEncoders (VAE).

 

"Unsupervised learning, in particular learning general nonlinear representations, is one of the deepest problems in machine learning. Estimating latent quantities in a generative model provides a principled framework, and has been successfully used in the linear case, e.g. with independent component analysis (ICA) and sparse coding. However, extending ICA to the nonlinear case has proven to be extremely difficult: A straight-forward extension is unidentifiable, i.e. it is not possible to recover those latent components that actually generated the data. Here, we show that this problem can be solved by using additional information either in the form of temporal structure or an additional, auxiliary variable. As a first approach, we formulate self-supervised learning schemes which are similar to those heuristically proposed in computer vision. Our main contribution is to provide a rigorous theoretical framework for such self-supervised algorithms, proving that they are able to solve the nonlinear ICA problem. We further show how a connection between nonlinear ICA and variational autoencoders (VAE): While ordinary VAE suffers from the lack of identifiability, conditioning by auxiliary variables leads to identifiability and provides another method for learning nonlinear ICA."

Nom de l'accordéon
Biography
Texte dans l'accordéon

Aapo Hyvarinen studied mathematics at the universities of Helsinki (Finland), Vienna (Austria), and Paris (France), and obtained a Ph.D. degree in Information Science at the Helsinki University of Technology in 1997.  From 2016 to 2019, he was Professor at the Gatsby Computational Neuroscience Unit, University College London, UK.  Currently he is visiting DATAIA at Inria-Saclay for a year.

Aapo Hyvarinen is the main author of the books « Independent Component Analysis » (2001) and « Natural Image Statistics » (2009), and author or coauthor of more than 200 scientific articles.  He is Action Editor at the Journal of Machine Learning Research and Neural Computation and Editorial Board Member in Foundations and Trends in Machine Learning. His current work concentrates on unsupervised machine learning and its applications to neuroscience.

Corps de texte

 

The seminar will take place on 9th October from 2pm to 4pm at Centre Inria-Saclay.

Registration free but mandatory within the limit of available seats
For security reasons, no access to the conference room for unregistered participants

Learn more
Corps de texte
News on the same topic