all AI news
Limitations of neural network training due to numerical instability of backpropagation. (arXiv:2210.00805v2 [cs.LG] UPDATED)
Oct. 7, 2022, 1:14 a.m. | Clemens Karner, Vladimir Kazeev, Philipp Christian Petersen
stat.ML updates on arXiv.org arxiv.org
We study the training of deep neural networks by gradient descent where
floating-point arithmetic is used to compute the gradients. In this framework
and under realistic assumptions, we demonstrate that it is highly unlikely to
find ReLU neural networks that maintain, in the course of training with
gradient descent, superlinearly many affine pieces with respect to their number
of layers. In virtually all approximation theoretical arguments which yield
high order polynomial rates of approximation, sequences of ReLU neural networks
with …
arxiv backpropagation network network training neural network numerical training
More from arxiv.org / stat.ML updates on arXiv.org
Estimation Sample Complexity of a Class of Nonlinear Continuous-time Systems
2 days, 15 hours ago |
arxiv.org
Jobs in AI, ML, Big Data
Data Architect
@ University of Texas at Austin | Austin, TX
Data ETL Engineer
@ University of Texas at Austin | Austin, TX
Lead GNSS Data Scientist
@ Lurra Systems | Melbourne
Senior Machine Learning Engineer (MLOps)
@ Promaton | Remote, Europe
Machine Learning Engineer (m/f/d)
@ StepStone Group | Düsseldorf, Germany
2024 GDIA AI/ML Scientist - Supplemental
@ Ford Motor Company | United States