all AI news
Implicit regularization of deep residual networks towards neural ODEs
March 4, 2024, 5:43 a.m. | Pierre Marion, Yu-Han Wu, Michael E. Sander, G\'erard Biau
cs.LG updates on arXiv.org arxiv.org
Abstract: Residual neural networks are state-of-the-art deep learning models. Their continuous-depth analog, neural ordinary differential equations (ODEs), are also widely used. Despite their success, the link between the discrete and continuous models still lacks a solid mathematical foundation. In this article, we take a step in this direction by establishing an implicit regularization of deep residual networks towards neural ODEs, for nonlinear networks trained with gradient flow. We prove that if the network is initialized as …
abstract analog art article arxiv continuous cs.lg deep learning differential foundation networks neural networks ordinary regularization residual solid state stat.ml success type
More from arxiv.org / cs.LG updates on arXiv.org
Sliced Wasserstein with Random-Path Projecting Directions
1 day, 21 hours ago |
arxiv.org
Learning Extrinsic Dexterity with Parameterized Manipulation Primitives
1 day, 21 hours ago |
arxiv.org
The Un-Kidnappable Robot: Acoustic Localization of Sneaking People
1 day, 21 hours ago |
arxiv.org
Jobs in AI, ML, Big Data
Data Engineer
@ Lemon.io | Remote: Europe, LATAM, Canada, UK, Asia, Oceania
Artificial Intelligence – Bioinformatic Expert
@ University of Texas Medical Branch | Galveston, TX
Lead Developer (AI)
@ Cere Network | San Francisco, US
Research Engineer
@ Allora Labs | Remote
Ecosystem Manager
@ Allora Labs | Remote
Founding AI Engineer, Agents
@ Occam AI | New York