all AI news
NeuroFlux: Memory-Efficient CNN Training Using Adaptive Local Learning
Feb. 23, 2024, 5:42 a.m. | Dhananjay Saikumar, Blesson Varghese
cs.LG updates on arXiv.org arxiv.org
Abstract: Efficient on-device convolutional neural network (CNN) training in resource-constrained mobile and edge environments is an open challenge. Backpropagation is the standard approach adopted, but it is GPU memory intensive due to its strong inter-layer dependencies that demand intermediate activations across the entire CNN model to be retained in GPU memory. This necessitates smaller batch sizes to make training possible within the available GPU memory budget, but in turn, results in a substantially high and impractical …
abstract arxiv backpropagation challenge cnn convolutional neural network cs.lg demand dependencies edge environments gpu intermediate layer memory mobile network neural network standard training type
More from arxiv.org / cs.LG updates on arXiv.org
The Perception-Robustness Tradeoff in Deterministic Image Restoration
1 day, 19 hours ago |
arxiv.org
Jobs in AI, ML, Big Data
Founding AI Engineer, Agents
@ Occam AI | New York
AI Engineer Intern, Agents
@ Occam AI | US
AI Research Scientist
@ Vara | Berlin, Germany and Remote
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