Data Symmetries and Learning in Fully Connected Neural Networks

Data Symmetries and Learning in Fully Connected Neural Networks

Symmetries in the data and how they constrain the learned weights of modern deep networks is still an open problem. In this work we study the simple case of fully connected shallow non-linear neural networks and consider two types of symmetries: full dataset symmetries where the dataset <inline-f...

Full description

Bibliographic Details
Main Authors: Fabio Anselmi, Luca Manzoni, Alberto D'onofrio, Alex Rodriguez, Giulio Caravagna, Luca Bortolussi, Francesca Cairoli
Format: Article
Language:English
Published: IEEE 2023-01-01
Series:IEEE Access
Subjects:
Artificial neural networks
symmetry invariance
equivariance
Online Access:https://ieeexplore.ieee.org/document/10122571/

Internet

https://ieeexplore.ieee.org/document/10122571/

Similar Items