Model selection and local optimality in learning dynamical systems using recurrent neural networks

被引：0
|
作者：
Yokoyama, T [1 ]
Takeshima, K [1 ]
Nakano, R [1 ]
机构：
[1] Nagoya Inst Technol, Showa Ku, Nagoya, Aichi 4668555, Japan
来源：
PROCEEDING OF THE 2002 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS, VOLS 1-3 | 2002年
关键词：
D O I：
10.1109/IJCNN.2002.1005619
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
We consider learning a dynamical system (DS) by a continuous-time recurrent neural network (RNN). An affine RNN (A-RNN), whose hidden units are linearly related to visible ones, is defined so that it always produces a DS. Learning a DS by an A-RNN is performed as a three-layer perceptron. This paper investigates model selection and local optima problem in the learning. The experiments showed that model selection can be exactly done by monitoring generalization performance and in the learning there exist much more local optima than expected.
引用
收藏
页码：1039 / 1044
页数：4
相关论文
共 50 条
  • [21] Dynamical consistent recurrent neural networks
    Zimmermann, HG
    Grothmann, R
    Schäfer, AM
    Tietz, C
    [J]. PROCEEDINGS OF THE INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), VOLS 1-5, 2005, : 1537 - 1541
  • [22] Observation error covariance specification in dynamical systems for data assimilation using recurrent neural networks
    Cheng, Sibo
    Qiu, Mingming
    [J]. NEURAL COMPUTING & APPLICATIONS, 2022, 34 (16): : 13149 - 13167
  • [23] Observation error covariance specification in dynamical systems for data assimilation using recurrent neural networks
    Sibo Cheng
    Mingming Qiu
    [J]. Neural Computing and Applications, 2022, 34 : 13149 - 13167
  • [24] Variable selection using feedforward and recurrent neural networks
    Munoz, A
    Czernichow, T
    [J]. ENGINEERING INTELLIGENT SYSTEMS FOR ELECTRICAL ENGINEERING AND COMMUNICATIONS, 1998, 6 (02): : 91 - 102
  • [25] CONTROL OF NONLINEAR DYNAMICAL-SYSTEMS MODELED BY RECURRENT NEURAL NETWORKS
    NIKOLAOU, M
    HANAGANDI, V
    [J]. AICHE JOURNAL, 1993, 39 (11) : 1890 - 1894
  • [26] Adaptive parallel identification of dynamical systems by adaptive recurrent neural networks
    Lo, JT
    Bassu, D
    [J]. PROCEEDINGS OF THE INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS 2003, VOLS 1-4, 2003, : 914 - 918
  • [27] Modeling of continuous time dynamical systems with input by recurrent neural networks
    Chow, TWS
    Li, XD
    [J]. IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS I-FUNDAMENTAL THEORY AND APPLICATIONS, 2000, 47 (04): : 575 - 578
  • [28] Robust Pinning Control of Complex Dynamical Networks using Recurrent Neural Networks
    Sanchez, Edgar N.
    Rodriguez, David I.
    [J]. 2014 IEEE SYMPOSIUM ON COMPUTATIONAL INTELLIGENCE IN CONTROL AND AUTOMATION (CICA), 2014, : 83 - 89
  • [29] A working memory model based on recurrent neural networks using reinforcement learning
    Wang, Mengyuan
    Wang, Yihong
    Xu, Xuying
    Pan, Xiaochuan
    [J]. COGNITIVE NEURODYNAMICS, 2024,
  • [30] Generic model for automated player selection for cricket teams using recurrent neural networks
    Vetukuri, V. Sivaramaraju
    Sethi, Nilambar
    Rajender, R.
    [J]. EVOLUTIONARY INTELLIGENCE, 2021, 14 (02) : 971 - 978
12345