UM  > Faculty of Science and Technology
Affiliated with RCfalse
Status申請中Pending
A method and device for training classification models and data classification
Kafeng Wang1; Chengzhong Xu2; Haoyi Xiong3; Xingjian Li4; Dejing Dou5
2023-12
CountryChina; USA
Subtype发明专利Invention
Abstract

This invention introduces a method and device for efficient training, which intends to make full use of DNN model’s capacity. Two specific techniques are proposed to tackle the problem. One is to train models with different scales by minimizing the cross-entropy loss. The other is to jointly optimize the data and model, in order to learn the relationship between the model complexity and data difficulty. The model is optimized to not only minimize the prediction error, but also reduce the inference time as much as possible. By employing this technique, easy data can be computed with simpler network for efficient inference and difficult data tend to select more complex network to ensure the accuracy.

KeywordDeep Learning Efficiency Neural Network Compression Dynamic Computing
Document TypePatent
CollectionFaculty of Science and Technology
Affiliation1.University of Macau
2.University of Macau
3.Baidu Research
4.University of Macau
5.Baidu Research
First Author AffilicationUniversity of Macau
Recommended Citation
GB/T 7714
Kafeng Wang,Chengzhong Xu,Haoyi Xiong,et al. A method and device for training classification models and data classification[P]. 2023-12-01.
APA Kafeng Wang,Chengzhong Xu,Haoyi Xiong,Xingjian Li,&Dejing Dou.A method and device for training classification models and data classification.
Files in This Item:
There are no files associated with this item.
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Kafeng Wang]'s Articles
[Chengzhong Xu]'s Articles
[Haoyi Xiong]'s Articles
Baidu academic
Similar articles in Baidu academic
[Kafeng Wang]'s Articles
[Chengzhong Xu]'s Articles
[Haoyi Xiong]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Kafeng Wang]'s Articles
[Chengzhong Xu]'s Articles
[Haoyi Xiong]'s Articles
Terms of Use
No data!
Social Bookmark/Share
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.