Showing cs.LGShow all
2 papers · 1 filter
cs.LG2025
An unsupervised tour through the hidden pathways of deep neural networks
Diego Doimo
The goal of this thesis is to improve our understanding of the internal mechanisms by which deep artificial neural networks create meaningful representations and are able to genera…
cs.LG2024
Understanding Variational Autoencoders with Intrinsic Dimension and Information Imbalance
Charles Camboulin, Diego Doimo, Aldo Glielmo
This work presents an analysis of the hidden representations of Variational Autoencoders (VAEs) using the Intrinsic Dimension (ID) and the Information Imbalance (II). We show that…