A novel HashedNets model based on the efficient hyperparameter optimization

  • Qin Fang
  • , Jianxia Chen
  • , Zhongbao Ma
  • , Chao Li
  • , Jie Zhang
  • , Yixin Chen
  • , Qiang Lv

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

The research of neural networks compression becomes a hot spot in the AI area. In this paper, we propose a novel method to optimize the hyperparameters of a compression Neural Networks called HashedNets with Radial Basis Function (RBF) interpolation model and Dynamic Coordinate Search (DYCORS) method, the proposed model is called HD-HORD which can help the HashedNets search for the best hyperparameters automatically and efficiently. Experimental results show that the efficiency of HD-HORD can be improved 72% faster than other methods.

Original languageEnglish
Title of host publication2017 4th International Conference on Systems and Informatics, ICSAI 2017
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1146-1151
Number of pages6
ISBN (Electronic)9781538611074
DOIs
StatePublished - Jun 28 2017
Event4th International Conference on Systems and Informatics, ICSAI 2017 - Hangzhou, China
Duration: Nov 11 2017Nov 13 2017

Publication series

Name2017 4th International Conference on Systems and Informatics, ICSAI 2017
Volume2018-January

Conference

Conference4th International Conference on Systems and Informatics, ICSAI 2017
Country/TerritoryChina
CityHangzhou
Period11/11/1711/13/17

Keywords

  • Dynamic Coordinate Search
  • HashedNets
  • hyperparameter optimization
  • nerural networks

Fingerprint

Dive into the research topics of 'A novel HashedNets model based on the efficient hyperparameter optimization'. Together they form a unique fingerprint.

Cite this