Fundamentals of Higher Order Neural Networks for Modeling and Simulation-Reference-Cited by-同舟云学术

Fundamentals of Higher Order Neural Networks for Modeling and Simulation

Published:2013 Issue: Volume: Page:103-133
ISSN:
Container-title:Artificial Higher Order Neural Networks for Modeling and Simulation
language:
Short-container-title:

Author:

Gupta Madan M.¹,Bukovsky Ivo²,Homma Noriyasu³,Solo Ashu M. G.⁴,Hou Zeng-Guang⁵

Affiliation:

1. University of Saskatchewan, Canada

2. Czech Technical University in Prague, Czech Republic

3. Tohoku University, Japan

4. Maverick Technologies America Inc., USA

5. The Chinese Academy of Sciences, China

Abstract

In this chapter, the authors provide fundamental principles of Higher Order Neural Units (HONUs) and Higher Order Neural Networks (HONNs) for modeling and simulation. An essential core of HONNs can be found in higher order weighted combinations or correlations between the input variables and HONU. Except for the high quality of nonlinear approximation of static HONUs, the capability of dynamic HONUs for the modeling of dynamic systems is shown and compared to conventional recurrent neural networks when a practical learning algorithm is used. In addition, the potential of continuous dynamic HONUs to approximate high dynamic order systems is discussed, as adaptable time delays can be implemented. By using some typical examples, this chapter describes how and why higher order combinations or correlations can be effective for modeling of systems.

Publisher

IGI Global

Reference33 articles.

1. Linear dynamic neural units with time delay for identification and control.;I.Bukovsky;Automatizace,2005

2. Bukovsky, I., Bila, J., & Gupta, M. M. (2006). Stable neural architecture of dynamic neural units with adaptive time delays. In Proceedings of the 7th International FLINS Conference on Applied Artificial Intelligence, (pp. 215-222). FLINS.

3. Foundation and Classification of Nonconventional Neural Units and Paradigm of Nonsynaptic Neural Interaction

4. Bukovsky, I., Homma, N., Smetana, L., Rodriguez, R., Mironovova, M., & Vrana, S. (2010b). Quadratic neural unit is a good compromise between linear models and neural networks for industrial applications. In Proceedings of the ICCI 2010: the 9th IEEE International Conference on Cognitive Informatics. Beijing, China: IEEE Press.

5. Bukovsky, I., & Simeunovic, G. (2006). Dynamic-order-extended time-delay dynamic neural units. In Proceedings of the 8th Seminar on Neural Network Applications in Electrical Engineering NEUREL-2006. IEEE Press.

Cited by 16 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献

1. Applications of Machine Learning in Subsurface Reservoir Simulation—A Review—Part II;Energies;2023-09-20

2. A Deep Learning Method for the Detection and Compensation of Outlier Events in Stock Data;Electronics;2022-10-26

3. NEWRON: A New Generalization of the Artificial Neuron to Enhance the Interpretability of Neural Networks;2022 International Joint Conference on Neural Networks (IJCNN);2022-07-18

4. Deterministic behavior of temperature field in turboprop engine via shallow neural networks;Neural Computing and Applications;2021-09-20

5. Novelty detection-based approach for Alzheimer’s disease and mild cognitive impairment diagnosis from EEG;Medical & Biological Engineering & Computing;2021-09-18