Vor Ort
Merkzettel Warenkorb
Produktbild: Mathematical Methods C

Mathematical Methods C

144,99 €

inkl. gesetzl. MwSt., Versandkostenfrei

Beschreibung

Produktdetails

Einband

Gebundene Ausgabe

Erscheinungsdatum

01.01.1900

Herausgeber

Snehashish Chakraverty

Verlag

John Wiley & Sons Inc

Seitenzahl

464

Maße (L/B/H)

25,4/20,3/2,5 cm

Gewicht

1157 g

Auflage

1. Auflage

Sprache

Englisch

ISBN

978-1-119-58550-3

Beschreibung

Produktdetails

Einband

Gebundene Ausgabe

Erscheinungsdatum

01.01.1900

Herausgeber

Snehashish Chakraverty

Verlag

John Wiley & Sons Inc

Seitenzahl

464

Maße (L/B/H)

25,4/20,3/2,5 cm

Gewicht

1157 g

Auflage

1. Auflage

Sprache

Englisch

ISBN

978-1-119-58550-3

Herstelleradresse

Libri GmbH
Europaallee 1
36244 Bad Hersfeld
DE

Email: gpsr@libri.de

Noch keine Bewertungen vorhanden

Verfassen Sie die erste Bewertung zu diesem Artikel

Helfen Sie anderen Kundinnen und Kunden durch Ihre Meinung.

Kundinnen und Kunden meinen

Bewertungen (0)
Die Leseprobe wird geladen.
  • Produktbild: Mathematical Methods C
  • Notes on Contributors xv
     
    Preface xxv
     
    Acknowledgments xxvii
     
    1 Connectionist Learning Models for Application Problems Involving Differential and Integral Equations 1
    Susmita Mall, Sumit Kumar Jeswal, and Snehashish Chakraverty
     
    1.1 Introduction 1
     
    1.1.1 Artificial Neural Network 1
     
    1.1.2 Types of Neural Networks 1
     
    1.1.3 Learning in Neural Network 2
     
    1.1.4 Activation Function 2
     
    1.1.4.1 Sigmoidal Function 3
     
    1.1.5 Advantages of Neural Network 3
     
    1.1.6 Functional Link Artificial Neural Network (FLANN) 3
     
    1.1.7 Differential Equations (DEs) 4
     
    1.1.8 Integral Equation 5
     
    1.1.8.1 Fredholm Integral Equation of First Kind 5
     
    1.1.8.2 Fredholm Integral Equation of Second Kind 5
     
    1.1.8.3 Volterra Integral Equation of First Kind 5
     
    1.1.8.4 Volterra Integral Equation of Second Kind 5
     
    1.1.8.5 Linear Fredholm Integral Equation System of Second Kind 6
     
    1.2 Methodology for Differential Equations 6
     
    1.2.1 FLANN-Based General Formulation of Differential Equations 6
     
    1.2.1.1 Second-Order Initial Value Problem 6
     
    1.2.1.2 Second-Order Boundary Value Problem 7
     
    1.2.2 Proposed Laguerre Neural Network (LgNN) for Differential Equations 7
     
    1.2.2.1 Architecture of Single-Layer LgNN Model 7
     
    1.2.2.2 Training Algorithm of Laguerre Neural Network (LgNN) 8
     
    1.2.2.3 Gradient Computation of LgNN 9
     
    1.3 Methodology for Solving a System of Fredholm Integral Equations of Second Kind 9
     
    1.3.1 Algorithm 10
     
    1.4 Numerical Examples and Discussion 11
     
    1.4.1 Differential Equations and Applications 11
     
    1.4.2 Integral Equations 16
     
    1.5 Conclusion 20
     
    References 20
     
    2 Deep Learning in Population Genetics: Prediction and Explanation of Selection of a Population 23
    Romila Ghosh and Satyakama Paul
     
    2.1 Introduction 23
     
    2.2 Literature Review 23
     
    2.3 Dataset Description 25
     
    2.3.1 Selection and Its Importance 25
     
    2.4 Objective 26
     
    2.5 Relevant Theory, Results, and Discussions 27
     
    2.5.1 automl 27
     
    2.5.2 Hypertuning the Best Model 28
     
    2.6 Conclusion 30
     
    References 30
     
    3 A Survey of Classification Techniques in Speech Emotion Recognition 33
    Tanmoy Roy, Tshilidzi Marwala, and Snehashish Chakraverty
     
    3.1 Introduction 33
     
    3.2 Emotional Speech Databases 33
     
    3.3 SER Features 34
     
    3.4 Classification Techniques 35
     
    3.4.1 Hidden Markov Model 36
     
    3.4.1.1 Difficulties in Using HMM for SER 37
     
    3.4.2 Gaussian Mixture Model 37
     
    3.4.2.1 Difficulties in Using GMM for SER 38
     
    3.4.3 Support Vector Machine 38
     
    3.4.3.1 Difficulties with SVM 39
     
    3.4.4 Deep Learning 39
     
    3.4.4.1 Drawbacks of Using Deep Learning for SER 41
     
    3.5 Difficulties in SER Studies 41
     
    3.6 Conclusion 41
     
    References 42
     
    4 Mathematical Methods in Deep Learning 49
    Srinivasa Manikant Upadhyayula and Kannan Venkataramanan
     
    4.1 Deep Learning Using Neural Networks 49
     
    4.2 Introduction to Neural Networks 49
     
    4.2.1 Artificial Neural Network (ANN) 50
     
    4.2.1.1 Activation Function 52
     
    4.2.1.2 Logistic Sigmoid Activation Function 52
     
    4.2.1.3 tanh or Hyperbolic Tangent Activation Function 53
     
    4.2.1.4 ReLU (Rectified Linear Unit) Activation Function 54
     
    4.3 Other Activation Functions (Variant Forms of ReLU) 55
     
    4.3.1 Smooth ReLU 55
     
    4.3.2 Noisy ReLU 55
     
    4.3.3 Leaky ReLU 55
     <