Cargando…
Decoupled neural network training with re-computation and weight prediction
To break the three lockings during backpropagation (BP) process for neural network training, multiple decoupled learning methods have been investigated recently. These methods either lead to significant drop in accuracy performance or suffer from dramatic increase in memory usage. In this paper, a n...
Autores principales: | Peng, Jiawei, Xu, Yicheng, Lin, Zhiping, Weng, Zhenyu, Yang, Zishuo, Zhuang, Huiping |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Public Library of Science
2023
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9949630/ https://www.ncbi.nlm.nih.gov/pubmed/36821537 http://dx.doi.org/10.1371/journal.pone.0276427 |
Ejemplares similares
-
Spectral decoupling for training transferable neural networks in medical imaging
por: Pohjonen, Joona, et al.
Publicado: (2022) -
A Block-Based Adaptive Decoupling Framework for Graph Neural Networks
por: Shen, Xu, et al.
Publicado: (2022) -
Computing of temporal information in spiking neural networks with ReRAM synapses
por: Wang, W., et al.
Publicado: (2019) -
A Universal Decoupled Training Framework for Human Parsing
por: Li, Yang, et al.
Publicado: (2022) -
Dynamic Weighting Network for Person Re-Identification
por: Li, Guang, et al.
Publicado: (2023)