TY - GEN
T1 - A novel HashedNets model based on the efficient hyperparameter optimization
AU - Fang, Qin
AU - Chen, Jianxia
AU - Ma, Zhongbao
AU - Li, Chao
AU - Zhang, Jie
AU - Chen, Yixin
AU - Lv, Qiang
N1 - Publisher Copyright:
© 2017 IEEE.
PY - 2017/6/28
Y1 - 2017/6/28
N2 - 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.
AB - 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.
KW - Dynamic Coordinate Search
KW - HashedNets
KW - hyperparameter optimization
KW - nerural networks
UR - https://www.scopus.com/pages/publications/85046634879
U2 - 10.1109/ICSAI.2017.8248458
DO - 10.1109/ICSAI.2017.8248458
M3 - Conference contribution
AN - SCOPUS:85046634879
T3 - 2017 4th International Conference on Systems and Informatics, ICSAI 2017
SP - 1146
EP - 1151
BT - 2017 4th International Conference on Systems and Informatics, ICSAI 2017
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 4th International Conference on Systems and Informatics, ICSAI 2017
Y2 - 11 November 2017 through 13 November 2017
ER -