|
|
|
|
| LEADER |
01000caa a22002652 4500 |
| 001 |
NLM355324202 |
| 003 |
DE-627 |
| 005 |
20231227133632.0 |
| 007 |
cr uuu---uuuuu |
| 008 |
231226s2023 xx |||||o 00| ||eng c |
| 024 |
7 |
|
|a 10.1109/TPAMI.2023.3250241
|2 doi
|
| 028 |
5 |
2 |
|a pubmed24n1231.xml
|
| 035 |
|
|
|a (DE-627)NLM355324202
|
| 035 |
|
|
|a (NLM)37027763
|
| 040 |
|
|
|a DE-627
|b ger
|c DE-627
|e rakwb
|
| 041 |
|
|
|a eng
|
| 100 |
1 |
|
|a Huang, Lei
|e verfasserin
|4 aut
|
| 245 |
1 |
0 |
|a Normalization Techniques in Training DNNs
|b Methodology, Analysis and Application
|
| 264 |
|
1 |
|c 2023
|
| 336 |
|
|
|a Text
|b txt
|2 rdacontent
|
| 337 |
|
|
|a ƒaComputermedien
|b c
|2 rdamedia
|
| 338 |
|
|
|a ƒa Online-Ressource
|b cr
|2 rdacarrier
|
| 500 |
|
|
|a Date Completed 17.12.2023
|
| 500 |
|
|
|a Date Revised 17.12.2023
|
| 500 |
|
|
|a published: Print-Electronic
|
| 500 |
|
|
|a Citation Status MEDLINE
|
| 520 |
|
|
|a Normalization techniques are essential for accelerating the training and improving the generalization of deep neural networks (DNNs), and have successfully been used in various applications. This paper reviews and comments on the past, present and future of normalization methods in the context of DNN training. We provide a unified picture of the main motivation behind different approaches from the perspective of optimization, and present a taxonomy for understanding the similarities and differences between them. Specifically, we decompose the pipeline of the most representative normalizing activation methods into three components: the normalization area partitioning, normalization operation and normalization representation recovery. In doing so, we provide insight for designing new normalization technique. Finally, we discuss the current progress in understanding normalization methods, and provide a comprehensive review of the applications of normalization for particular tasks, in which it can effectively solve the key issues
|
| 650 |
|
4 |
|a Review
|
| 650 |
|
4 |
|a Journal Article
|
| 700 |
1 |
|
|a Qin, Jie
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Zhou, Yi
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Zhu, Fan
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Liu, Li
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Shao, Ling
|e verfasserin
|4 aut
|
| 773 |
0 |
8 |
|i Enthalten in
|t IEEE transactions on pattern analysis and machine intelligence
|d 1979
|g 45(2023), 8 vom: 15. Aug., Seite 10173-10196
|w (DE-627)NLM098212257
|x 1939-3539
|7 nnns
|
| 773 |
1 |
8 |
|g volume:45
|g year:2023
|g number:8
|g day:15
|g month:08
|g pages:10173-10196
|
| 856 |
4 |
0 |
|u http://dx.doi.org/10.1109/TPAMI.2023.3250241
|3 Volltext
|
| 912 |
|
|
|a GBV_USEFLAG_A
|
| 912 |
|
|
|a SYSFLAG_A
|
| 912 |
|
|
|a GBV_NLM
|
| 912 |
|
|
|a GBV_ILN_350
|
| 951 |
|
|
|a AR
|
| 952 |
|
|
|d 45
|j 2023
|e 8
|b 15
|c 08
|h 10173-10196
|