Improved Initialization of State-Space Artificial Neural Networks

被引:0
|
作者
Schoukens, Maarten [1 ]
机构
[1] Eindhoven Univ Technol, Dept Elect Engn, NL-5612 AZ Eindhoven, Netherlands
基金
欧盟地平线“2020”;
关键词
NONLINEAR-SYSTEM IDENTIFICATION; MODELS;
D O I
暂无
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
The identification of black-box nonlinear state-space models requires a flexible representation of the state and output equation. Artificial neural networks have proven to provide such a representation. However, as in many identification problems, a nonlinear optimization problem needs to be solved to obtain the model parameters (layer weights and biases). A well-thought initialization of these model parameters can often avoid that the nonlinear optimization algorithm converges to a poorly performing local minimum of the considered cost function. This paper introduces an improved initialization approach for nonlinear state-space models represented as a recurrent artificial neural network and emphasizes the importance of including an explicit linear term in the model structure. Some of the neural network weights are initialized starting from a linear approximation of the nonlinear system, while others are initialized using random values or zeros. The effectiveness of the proposed initialization approach over previously proposed methods is illustrated on two benchmark examples.
引用
收藏
页码:1913 / 1918
页数:6
相关论文
共 50 条
  • [41] Bio-inspired Stochastic Growth and Initialization for Artificial Neural Networks
    Dai, Kevin
    Farimani, Amir Barati
    Webster-Wood, Victoria A.
    BIOMIMETIC AND BIOHYBRID SYSTEMS, LIVING MACHINES 2019, 2019, 11556 : 88 - 100
  • [42] On the effects of biased quantum random numbers on the initialization of artificial neural networks
    Heese, Raoul
    Wolter, Moritz
    Muecke, Sascha
    Franken, Lukas
    Piatkowski, Nico
    MACHINE LEARNING, 2024, 113 (03) : 1189 - 1217
  • [43] On the effects of biased quantum random numbers on the initialization of artificial neural networks
    Raoul Heese
    Moritz Wolter
    Sascha Mücke
    Lukas Franken
    Nico Piatkowski
    Machine Learning, 2024, 113 : 1189 - 1217
  • [44] A New Weight Initialization Method for Sigmoidal Feedforward Artificial Neural Networks
    Sodhi, Sartaj Singh
    Chandra, Pravin
    Tanwar, Sharad
    PROCEEDINGS OF THE 2014 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), 2014, : 291 - 298
  • [45] Reliability evaluation of multistate networks: An improved algorithm using state-space decomposition and experimental comparison
    Bai, Guanghan
    Tian, Zhigang
    Zuo, Ming J.
    IISE TRANSACTIONS, 2018, 50 (05) : 407 - 418
  • [46] On affine state-space neural networks for system identification: Global stability conditions and complexity management
    Gil, P.
    Henriques, J.
    Cardoso, A.
    Dourado, A.
    CONTROL ENGINEERING PRACTICE, 2013, 21 (04) : 518 - 529
  • [47] Physics-Guided State-Space Model Augmentation Using Weighted Regularized Neural Networks
    Liu, Yuhan
    Toth, Roland
    Schoukens, Maarten
    IFAC PAPERSONLINE, 2024, 58 (15): : 295 - 300
  • [48] Epistemic Uncertainty Quantification in State-Space LPV Model Identification Using Bayesian Neural Networks
    Bao, Yajie
    Velni, Javad Mohammadpour
    Shahbakhti, Mahdi
    IEEE CONTROL SYSTEMS LETTERS, 2021, 5 (02): : 719 - 724
  • [49] Thermal neural networks: Lumped-parameter thermal modeling with state-space machine learning
    Kirchgaessner, Wilhelm
    Wallscheid, Oliver
    Bocker, Joachim
    ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE, 2023, 117
  • [50] Modelling the unsteady lift of a pitching NACA 0018 aerofoil using state-space neural networks
    Damiola, Luca
    Decuyper, Jan
    Runacres, Mark
    De Troyer, Tim
    JOURNAL OF FLUID MECHANICS, 2024, 983