An efficient method for determining the optimal convolutional neural network structure based on Taguchi method

作     者：Lee, Pin-Chan Lo, Tzu-Ping Sun, Haoqing Wen, I-Jyh 

作者机构：Yuejin Technol Ltd Taipei Taiwan Southwest Jiaotong Univ Sch Civil Engn Chengdu Peoples R China Natl Yunlin Univ Sci & Technol Dept Construct Engn Touliu Yunlin Taiwan 

出 版 物：《JOURNAL OF INTELLIGENT & FUZZY SYSTEMS》 (智能与模糊系统杂志)

年 卷 期：2020年第39卷第3期

页      面：2611-2625页

核心收录：

学科分类：12[管理学] 1201[管理学-管理科学与工程(可授管理学、工学学位)] 08[工学] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

主　　题：Convolutional neural network hyperparameter combination optimization algorithm Taguchi method 

摘      要：Structure of convolutional neural network (CNN) applied for image recognition requires large numbers of tuning for designated datasets in practice. It is a time-consuming process to finally come up with a feasible structure for specific requirement. This paper proposes a method based on Taguchi method which can efficiently determine the optimal structure of hyperparameters combination. Five hyperparameters with four levels are defined as control factors and two indicators are chosen to measure the performance of CNN structure. L16(45) orthogonal array is used to arrange the experiment. S/N ratio and main effect plot are used to identify the optimal structure (hyperparameter combination) of CNN. The classic case of MNIST is employed to verify the practicability of the proposed method. Results show that the proposed method can identify the optimal CNN structure efficiently and also rank the significance priority of hyperparameters.