Cargando…

Mathematical Methods in Interdisciplinary Sciences

Brings mathematics to bear on your real-world, scientific problems Mathematical Methods in Interdisciplinary Sciences provides a practical and usable framework for bringing a mathematical approach to modelling real-life scientific and technological problems. The collection of chapters Dr. Snehashish...

Descripción completa

Detalles Bibliográficos
Clasificación:Libro Electrónico
Autor principal: Chakraverty, Snehashish
Formato: Electrónico eBook
Idioma:Inglés
Publicado: Newark : John Wiley & Sons, Incorporated, 2020.
Temas:
Acceso en línea:Texto completo
Tabla de Contenidos:
  • Cover
  • Title Page
  • Copyright
  • Contents
  • Notes on Contributors
  • Preface
  • Acknowledgments
  • Chapter 1 Connectionist Learning Models for Application Problems Involving Differential and Integral Equations
  • 1.1 Introduction
  • 1.1.1 Artificial Neural Network
  • 1.1.2 Types of Neural Networks
  • 1.1.3 Learning in Neural Network
  • 1.1.4 Activation Function
  • 1.1.4.1 Sigmoidal Function
  • 1.1.5 Advantages of Neural Network
  • 1.1.6 Functional Link Artificial Neural Network (FLANN)
  • 1.1.7 Differential Equations (DEs)
  • 1.1.8 Integral Equation
  • 1.1.8.1 Fredholm Integral Equation of First Kind
  • 1.1.8.2 Fredholm Integral Equation of Second Kind
  • 1.1.8.3 Volterra Integral Equation of First Kind
  • 1.1.8.4 Volterra Integral Equation of Second Kind
  • 1.1.8.5 Linear Fredholm Integral Equation System of Second Kind
  • 1.2 Methodology for Differential Equations
  • 1.2.1 FLANN-Based General Formulation of Differential Equations
  • 1.2.1.1 Second-Order Initial Value Problem
  • 1.2.1.2 Second-Order Boundary Value Problem
  • 1.2.2 Proposed Laguerre Neural Network (LgNN) for Differential Equations
  • 1.2.2.1 Architecture of Single-Layer LgNN Model
  • 1.2.2.2 Training Algorithm of Laguerre Neural Network (LgNN)
  • 1.2.2.3 Gradient Computation of LgNN
  • 1.3 Methodology for Solving a System of Fredholm Integral Equations of Second Kind
  • 1.3.1 Algorithm
  • 1.4 Numerical Examples and Discussion
  • 1.4.1 Differential Equations and Applications
  • 1.4.2 Integral Equations
  • 1.5 Conclusion
  • References
  • Chapter 2 Deep Learning in Population Genetics: Prediction and Explanation of Selection of a Population
  • 2.1 Introduction
  • 2.2 Literature Review
  • 2.3 Dataset Description
  • 2.3.1 Selection and Its Importance
  • 2.4 Objective
  • 2.5 Relevant Theory, Results, and Discussions
  • 2.5.1 automl
  • 2.5.2 Hypertuning the Best Model
  • 2.6 Conclusion
  • References
  • Chapter 3 A Survey of Classification Techniques in Speech Emotion Recognition
  • 3.1 Introduction
  • 3.2 Emotional Speech Databases
  • 3.3 SER Features
  • 3.4 Classification Techniques
  • 3.4.1 Hidden Markov Model
  • 3.4.1.1 Difficulties in Using HMM for SER
  • 3.4.2 Gaussian Mixture Model
  • 3.4.2.1 Difficulties in Using GMM for SER
  • 3.4.3 Support Vector Machine
  • 3.4.3.1 Difficulties with SVM
  • 3.4.4 Deep Learning
  • 3.4.4.1 Drawbacks of Using Deep Learning for SER
  • 3.5 Difficulties in SER Studies
  • 3.6 Conclusion
  • References
  • Chapter 4 Mathematical Methods in Deep Learning
  • 4.1 Deep Learning Using Neural Networks
  • 4.2 Introduction to Neural Networks
  • 4.2.1 Artificial Neural Network (ANN)
  • 4.2.1.1 Activation Function
  • 4.2.1.2 Logistic Sigmoid Activation Function
  • 4.2.1.3 tanh or Hyperbolic Tangent Activation Function
  • 4.2.1.4 ReLU (Rectified Linear Unit) Activation Function
  • 4.3 Other Activation Functions (Variant Forms of ReLU)
  • 4.3.1 Smooth ReLU