ResearchTrend.AI
Cockpit: A Practical Debugging Tool for the Training of Deep Neural Networks

Cockpit: A Practical Debugging Tool for the Training of Deep Neural Networks

Frank Schneider
Felix Dangel
Philipp Hennig
ArXivPDFHTML

Papers citing "Cockpit: A Practical Debugging Tool for the Training of Deep Neural Networks"

4 / 4 papers shown
Title
Position: Curvature Matrices Should Be Democratized via Linear Operators
Position: Curvature Matrices Should Be Democratized via Linear Operators
Felix Dangel
Runa Eschenhagen
Weronika Ormaniec
Andres Fernandez
Lukas Tatzel
Agustinus Kristiadi
69
3
0
31 Jan 2025
Going Further: Flatness at the Rescue of Early Stopping for Adversarial Example Transferability
Going Further: Flatness at the Rescue of Early Stopping for Adversarial Example Transferability
Martin Gubri
Maxime Cordy
Yves Le Traon
AAML
30
3
1
05 Apr 2023
Catastrophic Fisher Explosion: Early Phase Fisher Matrix Impacts Generalization
Catastrophic Fisher Explosion: Early Phase Fisher Matrix Impacts Generalization
Stanislaw Jastrzebski
Devansh Arpit
Oliver Åstrand
Giancarlo Kerg
Huan Wang
Caiming Xiong
R. Socher
Kyunghyun Cho
Krzysztof J. Geras
AI4CE
184
66
0
28 Dec 2020
On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minima
On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minima
N. Keskar
Dheevatsa Mudigere
J. Nocedal
M. Smelyanskiy
P. T. P. Tang
ODL
310
2,896
0
15 Sep 2016