Learning and predicting time series by neural networks

被引:0
|
作者
Freking, A [1 ]
Kinzel, W
Kanter, I
机构
[1] Univ Wurzburg, Inst Theoret Phys & Astrophys, D-97074 Wurzburg, Germany
[2] Bar Ilan Univ, Minerva Ctr, IL-52900 Ramat Gan, Israel
[3] Bar Ilan Univ, Dept Phys, IL-52900 Ramat Gan, Israel
来源
PHYSICAL REVIEW E | 2002年 / 65卷 / 05期
关键词
D O I
暂无
中图分类号
O35 [流体力学]; O53 [等离子体物理学];
学科分类号
070204 ; 080103 ; 080704 ;
摘要
Artificial neural networks which are trained on a time series are supposed to achieve two abilities: first, to predict the series many time steps ahead and second, to learn the rule which has produced the series. It is shown that prediction and learning are not necessarily related to each other. Chaotic sequences can be learned but not predicted while quasiperiodic sequences can be well predicted but not learned.
引用
收藏
页数:4
相关论文
共 50 条
  • [41] Time series forecasting with qubit neural networks
    Azevedo, Carlos R. B.
    Ferreira, Tiago A. E.
    PROCEDINGS OF THE 11TH IASTED INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE AND SOFT COMPUTING, 2007, : 13 - 18
  • [42] Time series prediction with granular neural networks
    Song, Mingli
    Li, Yan
    Pedrycz, Witold
    NEUROCOMPUTING, 2023, 546
  • [43] Modular Neural Networks in Time Series Modelling
    Averkin, Alexey
    Yarushev, Sergey
    2016 FIFTEENTH MEXICAN INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE (MICAI): ADVANCES IN ARTIFICIAL INTELLIGENCE, 2016, : 63 - 68
  • [44] Time Series Generation by Recurrent Neural Networks
    A. Priel
    I. Kanter
    Annals of Mathematics and Artificial Intelligence, 2003, 39 : 315 - 332
  • [45] Delayed time series predictions with neural networks
    Conway, AJ
    Macpherson, KP
    Brown, JC
    NEUROCOMPUTING, 1998, 18 (1-3) : 81 - 89
  • [46] Time series prediction with wavelet neural networks
    Cristea, P
    Tuduce, R
    Cristea, A
    NEUREL 2000: PROCEEDINGS OF THE 5TH SEMINAR ON NEURAL NETWORK APPLICATIONS IN ELECTRICAL ENGINEERING, 2000, : 7 - 10
  • [47] Recurrent neural networks for time series classification
    Hüsken, M
    Stagge, P
    NEUROCOMPUTING, 2003, 50 : 223 - 235
  • [48] Convolutional Neural Networks for Time Series Classification
    Zebik, Mariusz
    Korytkowski, Marcin
    Angryk, Rafal
    Scherer, Rafal
    ARTIFICIAL INTELLIGENCE AND SOFT COMPUTING, ICAISC 2017, PT II, 2017, 10246 : 635 - 642
  • [49] Time series identifying and modeling with neural networks
    Gao, DY
    Kinouchi, Y
    Ito, K
    Zhao, XL
    PROCEEDINGS OF THE INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS 2003, VOLS 1-4, 2003, : 2454 - 2459
  • [50] Convolutional neural networks for time series classification
    Zhao, Bendong
    Lu, Huanzhang
    Chen, Shangfeng
    Liu, Junliang
    Wu, Dongya
    JOURNAL OF SYSTEMS ENGINEERING AND ELECTRONICS, 2017, 28 (01) : 162 - 169