Research on the Generalization Problem of BP Neural Network

doi:10.1109/ACCESS.2024.3452710

	Research on the Generalization Problem of BP Neural Network
	Tian, Yanli1 ; Fu, Deyin1,2 ; Li, Guangzheng 3
	2024
发表期刊	IEEE ACCESS
卷号	12 页码:125416-125426
摘要	The application of neural network models is becoming increasingly widespread.One of the most relevant aspects of neural networks is their generalization ability, which predicts situations that are not included in the training set. Research has shown that training set samples play a dominant role in the learning and training of back propagation (BP) neural network model, and the information contained in them directly affects the network performance. A large number of similar samples not only prolongs the training time of the model, but also leads to problems such as decreased network generalization ability. Based on this, this study focused on the impact of training set samples on the generalization ability of the BP neural network model. A model was constructed on this basis by introducing dynamic clustering methods to screen the training set samples with representative and typical features. The empirical results indicate that using dynamic clustering methods to screen samples can effectively remove redundant information from the training set, enhance the network generalization ability, and improve the model prediction accuracy.Moreover, for large datasets, it can effectively improve the model's fitting degree and convergence speed, and enhance the noise tolerance performance of the BP neural network model.
关键词	Training data Predictive models Analytical models Biological neural networks Data models Artificial neural networks Noise measurement Boundary samples BP neural network model dynamic clustering training set
DOI	10.1109/ACCESS.2024.3452710
收录类别	SCIE ; EI
ISSN	2169-3536
语种	英语
WOS研究方向	Computer Science ; Engineering ; Telecommunications
WOS类目	Computer Science, Information Systems ; Engineering, Electrical & Electronic ; Telecommunications
WOS记录号	WOS:001316107300001
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
EI入藏号	20243817045283
EI主题词	Neural network models
EI分类号	1101
原始文献类型	Article
EISSN	2169-3536
引用统计	被引频次[WOS]：0 [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.lzufe.edu.cn/handle/39EH0E1M/38094
专题	统计与数据科学学院校领导
通讯作者	Tian, Yanli
作者单位	1.Lanzhou Univ Finance & Econ, Sch Stat & Data Sci, Lanzhou 730020, Peoples R China; 2.China Univ Lab Relat, Sch Lab Econ, Beijing 100048, Peoples R China; 3.Peoples Bank China, Gansu Branch, Lanzhou 730000, Peoples R China
第一作者单位	兰州财经大学
通讯作者单位	兰州财经大学
推荐引用方式 GB/T 7714	Tian, Yanli,Fu, Deyin,Li, Guangzheng. Research on the Generalization Problem of BP Neural Network[J]. IEEE ACCESS,2024,12:125416-125426.
APA	Tian, Yanli,Fu, Deyin,&Li, Guangzheng.(2024).Research on the Generalization Problem of BP Neural Network.IEEE ACCESS,12,125416-125426.
MLA	Tian, Yanli,et al."Research on the Generalization Problem of BP Neural Network".IEEE ACCESS 12(2024):125416-125426.