Stéphane d'Ascoli
Stéphane d'Ascoli
Bio
Research
Outreach
Music
Travel
CV
Light
Dark
Automatic
Jamming transition as a paradigm to understand the loss landscape of deep neural networks
Mario Geiger
,
Stefano Spigler
,
Stéphane d'Ascoli
,
Levent Sagun
,
Marco Baity-Jesi
,
Giulio Biroli
,
Matthieu Wyart
January 2019
Cite
Arxiv
Phys. Rev. E
Code
Type
Journal article
Publication
Physical Review E
Related
Scaling description of generalization with number of parameters in deep learning
Transformed CNNs: recasting pre-trained convolutional layers with self-attention
On the interplay between data structure and loss function in classification problems
ConViT: Improving Vision Transformers with Soft Convolutional Inductive Biases
Triple descent and the two kinds of overfitting: where and why do they appear?
Cite
×
