A Novel HashedNets Model Based on the Efficient Hyperparameter Optimization

被引：0

作者：

Fang, Qin ^{[1
]}

Chen, Jianxia ^{[1
]}

Ma, Zhongbao ^{[1
]}

Li, Chao ^{[1
]}

Zhang, Jie ^{[2
]}

Chen, Yixin ^{[3
]}

Lv, Qiang ^{[4
]}

机构：

[1] Hubei Univ Technol, Sch Comp Sci, Wuhan, Hubei, Peoples R China

[2] Hubei Univ Technol, Sch Elect Engn, Wuhan, Hubei, Peoples R China

[3] Washington Univ, Dept Comp Sci, St Louis, MO 63130 USA

[4] Yangzhou Univ, Coll Informat Engn, Yangzhou, Jiangsu, Peoples R China

来源：

2017 4TH INTERNATIONAL CONFERENCE ON SYSTEMS AND INFORMATICS (ICSAI) | 2017年

关键词：

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

D O I：

暂无

中图分类号：

TP301 [理论、方法];

学科分类号：

081202 ;

摘要：

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.

引用

页码：1146 / 1151

页数：6

共 27 条

[1] [Anonymous], 2017, Efficient processing of deep neural networks: A tutorial and survey
[2] [Anonymous], INT C ART INT STAT
[3] [Anonymous], 2013, NIPS
[4] [Anonymous], INT C INF COMM TECHN
[5] [Anonymous], STATISTICS
[6] [Anonymous], 2012, P 25 INT C NEURIPS
[7] [Anonymous], 2016, Efficient hyperparameter optimization of deep learning algorithms using deterministic rbf surrogates
[8] [Anonymous], ADV NEURAL INF PROCE
[9] [Anonymous], INT J INNOVATION TEC
[10] [Anonymous], J CIVIL ENG MANAGEME

← 1 2 3 →