CNN-FCM: System modeling promotes stability of deep learning in time series prediction

被引:39
作者
Liu, Penghui [1 ]
Liu, Jing [1 ]
Wu, Kai [1 ]
机构
[1] Xidian Univ, Sch Artificial Intelligence, Xian 710071, Peoples R China
基金
中国国家自然科学基金;
关键词
Fuzzy cognitive maps; Deep neural networks; Time series prediction; System modeling; FUZZY COGNITIVE MAPS; DESIGN;
D O I
10.1016/j.knosys.2020.106081
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Time series data are usually non-stationary and evolve over time. Even if deep learning has been found effective in dealing with sequential data, the stability of deep neural networks in coping with the situations unseen during the training stage is also important. This paper deals with this problem based on a fuzzy cognitive block (FCB) which embeds the learning of high-order fuzzy cognitive maps into the deep learning architecture. Thereafter, computers can automatically model the complex system that produces the observation rather than simply regress the available data. Respectively, we design a deep neural network termed CNN-FCM which has combined the available convolution network with FCB. To validate the advantages of our design and verify the effectiveness of FCB, twelve benchmark datasets are employed and classic deep learning architectures are introduced as the comparison. The experimental results show that the performance of many current popular deep learning architectures declines when handling data deviated from the training set. FCB plays an important role in promoting the performance of CNN-FCM in the corresponding experiments. Thereafter, we conclude that system modeling can promote the stability of deep learning in time series prediction. (C) 2020 Elsevier B.V. All rights reserved.
引用
收藏
页数:13
相关论文
共 51 条
[1]  
[Anonymous], 2017, MONTHLY CRITICAL RAD
[2]  
[Anonymous], 2017, S P 500 STOCK YAH
[3]  
[Anonymous], 2017, MONTHLY CLOSINGS DOW
[4]  
[Anonymous], 2017, CO2 PPM MAUNA LOA 19
[5]  
[Anonymous], 2017, MONTHLY MILK PRODUCT
[6]  
[Anonymous], 2017, MONTHLY LAKE ERIE LE
[7]  
Bai Shaojie, 2018, Universal language model fine-tuning for text classification
[8]   LEARNING LONG-TERM DEPENDENCIES WITH GRADIENT DESCENT IS DIFFICULT [J].
BENGIO, Y ;
SIMARD, P ;
FRASCONI, P .
IEEE TRANSACTIONS ON NEURAL NETWORKS, 1994, 5 (02) :157-166
[9]   Variational Inference: A Review for Statisticians [J].
Blei, David M. ;
Kucukelbir, Alp ;
McAuliffe, Jon D. .
JOURNAL OF THE AMERICAN STATISTICAL ASSOCIATION, 2017, 112 (518) :859-877
[10]   DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs [J].
Chen, Liang-Chieh ;
Papandreou, George ;
Kokkinos, Iasonas ;
Murphy, Kevin ;
Yuille, Alan L. .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2018, 40 (04) :834-848