Summer School on Model-Guided Data Science

Como, 2-6 September 2019

Unsupervised learning of features from data:
a statistical physics approach

R. Monasson

Extracting statistical features from unlabelled data is a major challenge in machine learning. I will show how statistical physics-based approaches can be helpful to understand the operation of various learning algorithms including principal component analysis, independent component analysis, auto-encoders, restricted Boltzmann machines. The lectures will both show applications and theory based on the tools and concepts of the statistical mechanics of disordered systems.
Suggestions for further readings:
Self-references: