微信服务号

微信订阅号

2025-4-3- 20
Home > Archive>Volume 31, Issue 7, 2020 >2157-2168. DOI:10.13328/j.cnki.jos.005822
PDF HTML XML Export Cite reminder
Easy Way for Multilayer Gradient Supplies
Author:
Affiliation:

Fund Project:

National Natural Science Foundation of China (61663046, 61876166); Yunnan Applied Fundamental Research Project (2016FB104); Yunnan Provincial Young Academic and Technical Leaders Reserve Talents (2017HB005); Yunnan Provincial Innovation Team (2017HC012); Yunnan Provincial University Key Laboratory Construction Plan Fund

  • Article
    • | |
  • Metrics
    • |
  • Reference
    • |
  • Related
    • |
  • Cited by
    • | |
  • Comments
    Abstract:

    Deep learning allows computational models that are composed of multiple processing layers to learn representations of data with multiple levels of abstraction. These have dramatically improved the state-of-the-art methods in speech recognition, visual object recognition, natural language processing, and many other domains. However, due to the large number of layers and large parameter scales, deep learning often results in gradient vanishing, falling into local optimal solution, overfitting, and so on. By using ensemble learning methods, this study proposes a novel deep sharing ensemble network. Through joint training many independent output layers in each hidden layer and injecting gradients, this network can reduce the gradient vanishing phenomenon, and through ensemble multi-output, it can get a better generalization performance.

    Reference
    Related
    Cited by
Get Citation

杜飞,杨云,胡媛媛,曹丽娟.一种简单的共享式多层梯度补给方法.软件学报,2020,31(7):2157-2168

Copy
Share
Article Metrics
  • Abstract:
  • PDF:
  • HTML:
  • Cited by:
History
  • Received:November 07,2017
  • Revised:March 11,2018
  • Online: July 11,2020
  • Published: July 06,2020
Links:Institute of Software, CASChina Computer FederationCASNSFC
You are the firstVisitors
Copyright: Institute of Software, Chinese Academy of Sciences Beijing ICP No. 05046678-4
Address：4# South Fourth Street, Zhong Guan Cun, Beijing 100190,Postal Code：100190
Phone：010-62562563 Fax：010-62562533 Email：jos@iscas.ac.cn
Technical Support：Beijing Qinyun Technology Development Co., Ltd.

Beijing Public Network Security No. 11040202500063