Artificial Neural Networks for Engineers and Scientists

Solving Ordinary Differential Equations
 
 
Routledge Member of the Taylor and Francis Group (Verlag)
  • 1. Auflage
  • |
  • erschienen am 20. Juli 2017
  • |
  • 168 Seiten
 
E-Book | PDF mit Adobe-DRM | Systemvoraussetzungen
978-1-4987-8140-4 (ISBN)
 
Differential equations play a vital role in the fields of engineering and science. Problems in engineering and science can be modeled using ordinary or partial differential equations. Analytical solutions of differential equations may not be obtained easily, so numerical methods have been developed to handle them. Machine intelligence methods, such as Artificial Neural Networks (ANN), are being used to solve differential equations, and these methods are presented in Artificial Neural Networks for Engineers and Scientists: Solving Ordinary Differential Equations. This book shows how computation of differential equation becomes faster once the ANN model is properly developed and applied.
  • Englisch
  • New York
  • |
  • USA
Taylor & Francis Inc
  • Für höhere Schule und Studium
  • 80 s/w Abbildungen
  • |
  • 80 schwarz-weiße Abbildungen
  • 9,16 MB
978-1-4987-8140-4 (9781498781404)
weitere Ausgaben werden ermittelt

Dr. S. Chakraverty has over 25 years of experience as a researcher and teacher. Currently, he is working at the National Institute of Technology, Rourkela, Odisha as a full Professor and Head of the Department of Mathematics. Prior to this, he was with CSIRCentral Building Research Institute, Roorkee, India. After graduating from St. Columba's College (Ranchi University), he obtained his M. Sc in Mathematics and M. Phil in Computer Applications from the University of Roorkee (now the Indian Institute of Technology Roorkee), earning First Position in the University honors. Dr. Chakraverty received his Ph. D. from IIT Roorkee in 1992. Afterwards, he did his post-doctoral research at Institute of Sound and Vibration Research (ISVR), University of Southampton, U.K. and at the Faculty of Engineering and Computer Science, Concordia University, Canada. He was also a visiting professor at Concordia and McGill Universities, Canada, during 1997-1999 and visiting professor of University of Johannesburg, South Africa during 2011-2014.

Mrs. Susmita Mall received her M. Sc. degree in Mathematics from Ravenshaw University, Cuttack, Odisha, India in 2003. Currently she is a Senior Research Fellow in National Institute of Technology, Rourkela - 769 008, Odisha, India. She has been awarded Women Scientist Scheme-A (WOS-A) fellowship, under Department of Science and Technology (DST), Government of India to undertake her Ph. D. studies. Her current research interest includes Mathematical Modeling, Artificial Neural Network, Differential equations and Numerical analysis. To date, she has published seven research papers in international refereed journals and five in conferences.

1. Preliminaries of Artificial Neural Network

1.1 Introduction

1.2 Architecture of ANN

1.2.1 Feed-Forward Neural Network

1.2.2 Feedback Neural Network

1.3 Paradigms of Learning

1.3.1 Supervised Learning or Associative Learning

1.3.2 Unsupervised or Self-Organization Learning

1.4 Learning Rules or Learning Processes

1.4.1 Error Back-Propagation Learning Algorithm or Delta

Learning Rule

1.5 Activation Functions

1.5.1 Sigmoid Function

1.5.1.1 Unipolar Sigmoid Function

1.5.1.2 Bipolar Sigmoid Function

1.5.2 Tangent Hyperbolic Function

References

2. Preliminaries of Ordinary Differential Equations

2.1 Definitions

2.1.1 Order and Degree of DEs

2.1.2 Ordinary Differential Equation

2.1.3 Partial Differential Equation

2.1.4 Linear and Nonlinear Differential Equations

2.1.5 Initial Value Problem

2.1.6 Boundary Value Problem

References

3. Multilayer Artificial Neural Network

3.1 Structure of Multilayer ANN Model

3.2 Formulations and Learning Algorithm of Multilayer

ANN Model

3.2.1 General Formulation of ODEs Based on ANN Model

3.2.2 Formulation of nth-Order IVPs

3.2.2.1 Formulation of First-Order IVPs

3.2.2.2 Formulation of Second-Order IVPs

3.2.3 Formulation of BVPs

3.2.3.1 Formulation of Second-Order BVPs

3.2.3.2 Formulation of Fourth-Order BVPs

3.2.4 Formulation of a System of First-Order ODEs

3.2.5 Computation of Gradient of ODEs for Multilayer

ANN Model

3.3 First-Order Linear ODEs

3.4 Higher-Order ODEs

3.5 System of ODEs

References

4. Regression-Based ANN

4.1 Algorithm of RBNN Model

4.2 Structure of RBNN Model

4.3 Formulation and Learning Algorithm of RBNN Model

4.4 Computation of Gradient for RBNN Model

4.5 First-Order Linear ODEs

4.6 Higher-Order Linear ODEs

References

5. Single-Layer Functional Link Artificial Neural Network

5.1 Single-Layer FLANN Models

5.1.1 ChNN Model

5.1.1.1 Structure of the ChNN Model

5.1.1.2 Formulation of the ChNN Model

5.1.1.3 Gradient Computation of the ChNN Model

5.1.2 LeNN Model

5.1.2.1 Structure of the LeNN Model

5.1.2.2 Formulation of the LeNN Model

5.1.2.3 Gradient Computation of the LeNN Model

5.1.3 HeNN Model

5.1.3.1 Architecture of the HeNN Model

5.1.3.2 Formulation of the HeNN Model

5.1.4 Simple Orthogonal Polynomial-Based Neural

Network (SOPNN) Model

5.1.4.1 Structure of the SOPNN Model

5.1.4.2 Formulation of the SOPNN Model

5.1.4.3 Gradient Computation of the SOPNN Model

5.2 First-Order Linear ODEs

5.3 Higher-Order ODEs

5.4 System of ODEs

References

6. Single-Layer Functional Link Artificial Neural Network

with Regression-Based Weights

6.1 ChNN Model with Regression-Based Weights

6.1.1 Structure of the ChNN Model

6.1.2 Formulation and Gradient Computation

of the ChNN Model

6.2 First-Order Linear ODEs

6.3 Higher-Order ODEs

References

7. Lane-Emden Equations

7.1 Multilayer ANN-Based Solution of Lane-Emden Equations

7.2 FLANN-Based Solution of Lane-Emden Equations

7.2.1 Homogeneous Lane-Emden Equations

7.2.2 Nonhomogeneous Lane-Emden Equation

References

8. Emden-Fowler Equations

8.1 Multilayer ANN-Based Solution of Emden-Fowler

Equations

8.2 FLANN-Based Solution of Emden-Fowler Equations

References

9. Duffing Oscillator Equations

9.1 Governing Equation

9.2 Unforced Duffing Oscillator Equations

9.3 Forced Duffing Oscillator Equations

References

10. Van der Pol-Duffing Oscillator Equation

10.1 Model Equation

10.2 Unforced Van der Pol-Duffing Oscillator Equation

10.3 Forced Van der Pol-Duffing Oscillator Equation

References

Dateiformat: PDF
Kopierschutz: Adobe-DRM (Digital Rights Management)

Systemvoraussetzungen:

Computer (Windows; MacOS X; Linux): Installieren Sie bereits vor dem Download die kostenlose Software Adobe Digital Editions (siehe E-Book Hilfe).

Tablet/Smartphone (Android; iOS): Installieren Sie bereits vor dem Download die kostenlose App Adobe Digital Editions (siehe E-Book Hilfe).

E-Book-Reader: Bookeen, Kobo, Pocketbook, Sony, Tolino u.v.a.m. (nicht Kindle)

Das Dateiformat PDF zeigt auf jeder Hardware eine Buchseite stets identisch an. Daher ist eine PDF auch für ein komplexes Layout geeignet, wie es bei Lehr- und Fachbüchern verwendet wird (Bilder, Tabellen, Spalten, Fußnoten). Bei kleinen Displays von E-Readern oder Smartphones sind PDF leider eher nervig, weil zu viel Scrollen notwendig ist. Mit Adobe-DRM wird hier ein "harter" Kopierschutz verwendet. Wenn die notwendigen Voraussetzungen nicht vorliegen, können Sie das E-Book leider nicht öffnen. Daher müssen Sie bereits vor dem Download Ihre Lese-Hardware vorbereiten.

Bitte beachten Sie bei der Verwendung der Lese-Software Adobe Digital Editions: wir empfehlen Ihnen unbedingt nach Installation der Lese-Software diese mit Ihrer persönlichen Adobe-ID zu autorisieren!

Weitere Informationen finden Sie in unserer E-Book Hilfe.


Download (sofort verfügbar)

127,99 €
inkl. 5% MwSt.
Download / Einzel-Lizenz
PDF mit Adobe-DRM
siehe Systemvoraussetzungen
E-Book bestellen