A learning algorithm for improved recurrent neural networks

被引：0
|
作者：
Chen, CH
Yu, LW
机构：
来源：
1997 IEEE INTERNATIONAL CONFERENCE ON NEURAL NETWORKS, VOLS 1-4 | 1997年
关键词：
D O I：
暂无
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
An improved recurrent neural network structure is proposed. The exact form of a gradient-following learning algorithm for the continuously running neural networks is derived for temporal supervised learning tasks. The algorithm allows networks to learn complex tasks that require the retention of information over time periods. The algorithm also compensates for the information that is missed by the traditional recurrent neural networks. Empirical results show that the networks trained using this algorithm have improved prediction performance over the backpropagation trained network and the Elman recurrent neural network.
引用
收藏
页码：2198 / 2202
页数：5
相关论文
共 50 条
  • [31] A Novel Fractional Gradient-Based Learning Algorithm for Recurrent Neural Networks
    Khan, Shujaat
    Ahmad, Jawwad
    Naseem, Imran
    Moinuddin, Muhammad
    CIRCUITS SYSTEMS AND SIGNAL PROCESSING, 2018, 37 (02) : 593 - 612
  • [32] TRTRL: A localized resource-efficient learning algorithm for recurrent neural networks
    Budik, Danny
    Elhanany, Itamar
    IEEE MWSCAS'06: PROCEEDINGS OF THE 2006 49TH MIDWEST SYMPOSIUM ON CIRCUITS AND SYSTEMS,, 2006, : 371 - +
  • [33] A Supervised Multi-spike Learning Algorithm for Recurrent Spiking Neural Networks
    Lin, Xianghong
    Shi, Guoyong
    ARTIFICIAL NEURAL NETWORKS AND MACHINE LEARNING - ICANN 2018, PT I, 2018, 11139 : 222 - 234
  • [34] A generalized cost criterion based learning algorithm for diagonal recurrent neural networks
    Wang, YJ
    Wang, H
    INTERNATIONAL CONFERENCE ON SENSORS AND CONTROL TECHNIQUES (ICSC 2000), 2000, 4077 : 482 - 485
  • [35] A Novel Fractional Gradient-Based Learning Algorithm for Recurrent Neural Networks
    Shujaat Khan
    Jawwad Ahmad
    Imran Naseem
    Muhammad Moinuddin
    Circuits, Systems, and Signal Processing, 2018, 37 : 593 - 612
  • [36] Learning with recurrent neural networks - Conclusion
    不详
    LEARNING WITH RECURRENT NEURAL NETWORKS, 2000, 254 : 133 - 135
  • [37] Bayesian learning for recurrent neural networks
    Crucianu, M
    Boné, R
    de Beauville, JPA
    NEUROCOMPUTING, 2001, 36 (01) : 235 - 242
  • [38] Learning with recurrent neural networks - Introduction
    Hammer, B
    LEARNING WITH RECURRENT NEURAL NETWORKS, 2000, 254 : 1 - +
  • [39] LEARNING COMPACT RECURRENT NEURAL NETWORKS
    Lu, Zhiyun
    Sindhwani, Vikas
    Sainath, Tara N.
    2016 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING PROCEEDINGS, 2016, : 5960 - 5964
  • [40] A new boosting algorithm for improved time-series forecasting with recurrent neural networks
    Assaad, Mohammad
    Bone, Romuald
    Cardot, Hubert
    INFORMATION FUSION, 2008, 9 (01) : 41 - 55
12345