Title :
Neural network pruning using MV regularizer
Author :
Nagata, Takashi ; Kawata, Atsushi ; Yamada, Ken-ichi ; Nakano, Ryohei
Author_Institution :
Nagoya Inst. of Technol., Japan
fDate :
6/24/1905 12:00:00 AM
Abstract :
Proposes a method of neural network pruning by using a strong regularizer called the MV regularizer. The MV regularizer learns a distinct penalty factor attached to each weight by solving a minimization problem over the validation error. After the learning, penalty factors are used to prune network weights one by one by monitoring generalization performance. Experiments using artificial data and real data showed the proposed method worked very well to remove a number of insignificant weights without the loss of generalization
Keywords :
learning (artificial intelligence); minimisation; neural nets; MV regularizer; generalization performance; minimization problem; neural network pruning; penalty factor; strong regularizer; validation error; weights pruning; Degradation; Ear; Monitoring; Multilayer perceptrons; Neodymium; Neural networks; Paper technology; Testing; Training data;
Conference_Titel :
Neural Networks, 2002. IJCNN '02. Proceedings of the 2002 International Joint Conference on
Conference_Location :
Honolulu, HI
Print_ISBN :
0-7803-7278-6
DOI :
10.1109/IJCNN.2002.1005621