Search Results for author:
Found 3 papers, 3 papers with code
The Training Process of Many Deep Networks Explores the Same Low-Dimensional Manifold
We develop information-geometric techniques to analyze the trajectories of the predictions of deep networks during training.
A picture of the space of typical learnable tasks
We develop information geometric techniques to understand the representations learned by deep networks when they are trained on different tasks using supervised, meta-, semi-supervised and contrastive learning.
Does the Data Induce Capacity Control in Deep Learning?
This structure is mirrored in a network trained on this data: we show that the Hessian and the Fisher Information Matrix (FIM) have eigenvalues that are spread uniformly over exponentially large ranges.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
