ProfessorsProfessors of École Polytechnique Fédérale de LausanneLeonardo Petrini

Leonardo Petrini

École Polytechnique Fédérale de Lausanne

H-index: 4

Europe-Switzerland

About Leonardo Petrini

Leonardo Petrini, With an exceptional h-index of 4 and a recent h-index of 4 (since 2020), a distinguished researcher at École Polytechnique Fédérale de Lausanne, specializes in the field of Neural Networks, Deep Learning, Statistical Physics.

His recent articles reflect a diverse array of research interests and contributions to the field:

Learning sparse features can lead to overfitting in neural networks

How deep convolutional neural networks lose spatial information with training

Breaking the Curse of Dimensionality in Deep Neural Networks by Learning Invariant Representations

How deep neural networks learn compositional data: the random hierarchy model

Diffeomorphisms invariance is a proxy of performance in deep neural networks

Landscape and training regimes in deep learning

Geometric compression of invariant manifolds in neural networks

How neural nets compress invariant manifolds

Leonardo Petrini Information

University	École Polytechnique Fédérale de Lausanne
Position	PhD Student Physics of Complex Systems Lab @
Citations(all)	99
Citations(since 2020)	99
Cited By	8
hIndex(all)	4
hIndex(since 2020)	4
i10Index(all)	3
i10Index(since 2020)	3
Email	Access Email
University Profile Page	École Polytechnique Fédérale de Lausanne
Google Scholar	View Google Scholar Profile

Leonardo Petrini Skills & Research Interests

Neural Networks

Deep Learning

Statistical Physics

Top articles of Leonardo Petrini

Title	Journal	Author(s)	Publication Date
Learning sparse features can lead to overfitting in neural networks	Journal of Statistical Mechanics: Theory and Experiment	Leonardo Petrini Francesco Cagnetta Eric Vanden-Eijnden Matthieu Wyart	2023/11/15
How deep convolutional neural networks lose spatial information with training	Machine Learning: Science and Technology	Umberto M Tomasini Leonardo Petrini Francesco Cagnetta Matthieu Wyart	2023/11/9
Breaking the Curse of Dimensionality in Deep Neural Networks by Learning Invariant Representations	arXiv preprint arXiv:2310.16154	Leonardo Petrini	2023/10/24
How deep neural networks learn compositional data: the random hierarchy model	arXiv e-prints	Francesco Cagnetta Leonardo Petrini Umberto M Tomasini Alessandro Favero Matthieu Wyart	2023/7
Diffeomorphisms invariance is a proxy of performance in deep neural networks	APS March Meeting Abstracts	Leonardo Petrini Alessandro Favero Mario Geiger Matthieu Wyart	2023
Landscape and training regimes in deep learning		Mario Geiger Leonardo Petrini Matthieu Wyart	2021/8/15
Geometric compression of invariant manifolds in neural networks	Journal of Statistical Mechanics: Theory and Experiment	Jonas Paccolat Leonardo Petrini Mario Geiger Kevin Tyloo Matthieu Wyart	2021/4/26
How neural nets compress invariant manifolds	APS March Meeting Abstracts	Jonas Paccolat Leonardo Petrini Mario Geiger Kevin Tyloo Matthieu Wyart	2021