Time series generation by recurrent neural networks

被引：5
|
作者：
Priel, A [1 ]
Kanter, I
机构：
[1] Bar Ilan Univ, Dept Phys, IL-52900 Ramat Gan, Israel
[2] Bar Ilan Univ, Minerva Ctr, IL-52900 Ramat Gan, Israel
[3] Bar Ilan Univ, Ctr Brain Sci, Ramat Gan, Israel
来源：
ANNALS OF MATHEMATICS AND ARTIFICIAL INTELLIGENCE | 2003年 / 39卷 / 03期
关键词：
recurrent neural networks; time series; asymptotic properties; non-linear dynamical systems; attractor dimension; stochastic processes;
D O I：
10.1023/A:1024620813258
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
The properties of time series, generated by continuous valued feed-forward networks in which the next input vector is determined from past output values, are studied. Asymptotic solutions developed suggest that the typical stable behavior is ( quasi) periodic with attractor dimension that is limited by the number of hidden units, independent of the details of the weights. The results are robust under additive noise, except for expected noise-induced effects - attractor broadening and loss of phase coherence at large times. These effects, however, are moderated by the size of the network N.
引用
收藏
页码：315 / 332
页数：18
相关论文
共 50 条
  • [1] Time Series Generation by Recurrent Neural Networks
    A. Priel
    I. Kanter
    [J]. Annals of Mathematics and Artificial Intelligence, 2003, 39 : 315 - 332
  • [2] Recurrent neural networks for time series classification
    Hüsken, M
    Stagge, P
    [J]. NEUROCOMPUTING, 2003, 50 : 223 - 235
  • [3] Boosting recurrent neural networks for time series prediction
    Boné, R
    Assaad, M
    Crucianu, M
    [J]. ARTIFICIAL NEURAL NETS AND GENETIC ALGORITHMS, PROCEEDINGS, 2003, : 18 - 22
  • [4] Recurrent Neural Networks for Meteorological Time Series Imputation
    Flores, Anibal
    Tito, Hugo
    Centty, Deymor
    [J]. INTERNATIONAL JOURNAL OF ADVANCED COMPUTER SCIENCE AND APPLICATIONS, 2020, 11 (03) : 482 - 487
  • [5] Robust recurrent neural networks for time series forecasting
    Zhang, Xueli
    Zhong, Cankun
    Zhang, Jianjun
    Wang, Ting
    Ng, Wing W. Y.
    [J]. NEUROCOMPUTING, 2023, 526 : 143 - 157
  • [6] Recurrent Neural Networks for Multivariate Time Series with Missing Values
    Che, Zhengping
    Purushotham, Sanjay
    Cho, Kyunghyun
    Sontag, David
    Liu, Yan
    [J]. SCIENTIFIC REPORTS, 2018, 8
  • [7] Ensembles of Recurrent Neural Networks for Robust Time Series Forecasting
    Krstanovic, Sascha
    Paulheim, Heiko
    [J]. ARTIFICIAL INTELLIGENCE XXXIV, AI 2017, 2017, 10630 : 34 - 46
  • [8] Random Projection Recurrent Neural Networks for Time Series Classification
    Ma, Ye
    Hu, Moufa
    Chang, Qing
    Lu, Huanzhang
    [J]. 2018 8TH INTERNATIONAL CONFERENCE ON ELECTRONICS INFORMATION AND EMERGENCY COMMUNICATION (ICEIEC), 2018, : 40 - 43
  • [9] Robust Online Time Series Prediction with Recurrent Neural Networks
    Guo, Tian
    Xu, Zhao
    Yao, Xin
    Chen, Haifeng
    Aberer, Karl
    Funaya, Koichi
    [J]. PROCEEDINGS OF 3RD IEEE/ACM INTERNATIONAL CONFERENCE ON DATA SCIENCE AND ADVANCED ANALYTICS, (DSAA 2016), 2016, : 816 - 825
  • [10] Predicting chaotic time series by boosted recurrent neural networks
    Assaad, Mohammad
    Bone, Romuald
    Cardot, Hubert
    [J]. NEURAL INFORMATION PROCESSING, PT 2, PROCEEDINGS, 2006, 4233 : 831 - 840
12345