Artificial neural networks : a practical course

• Main Authors: Silva, Ivan Nunes Da (Author), Spatti, Danilo Hernane (Author), Andrade Flauzino, Rogerio (Author), Liboni, Luisa Helena Bartocci (Author), Reis Alves, Silas Franco dos (Author)
• Format: Electronic eBook
• Language: English
• Published: Switzerland : Springer, [2016]
• Subjects: Neural networks (Computer science); elektronické knihy; electronic books
• ISBN: 9783319431628; 9783319431611
• Physical Description: 1 online resource (xx, 307 pages) : illustrations (some color)

This book provides comprehensive coverage of neural networks, their evolution, their structure, the problems they can solve, and their applications. The first half of the book looks at theoretical investigations on artificial neural networks and addresses the key architectures that are capable of im...

Table of Contents:

• Intro; Preface; Organization; Acknowledgments; Contents; About the Authors; Architectures of Artificial Neural Networks and Their Theoretical Aspects; 1 Introduction; 1.1 Fundamental Theory; 1.1.1 Key Features; 1.1.2 Historical Overview; 1.1.3 Potential Application Areas; 1.2 Biological Neuron; 1.3 Artificial Neuron; 1.3.1 Partially Differentiable Activation Functions; 1.3.2 Fully Differentiable Activation Functions; 1.4 Performance Parameters; 1.5 Exercises; 2 Artificial Neural Network Architectures and Training Processes; 2.1 Introduction
• 2.2 Main Architectures of Artificial Neural Networks2.2.1 Single-Layer Feedforward Architecture; 2.2.2 Multiple-Layer Feedforward Architectures; 2.2.3 Recurrent or Feedback Architecture; 2.2.4 Mesh Architectures; 2.3 Training Processes and Properties of Learning; 2.3.1 Supervised Learning; 2.3.2 Unsupervised Learning; 2.3.3 Reinforcement Learning; 2.3.4 Offline Learning; 2.3.5 Online Learning; 2.4 Exercises; 3 The Perceptron Network; 3.1 Introduction; 3.2 Operating Principle of the Perceptron; 3.3 Mathematical Analysis of the Perceptron; 3.4 Training Process of the Perceptron; 3.5 Exercises
• 3.6 Practical Work4 The ADALINE Network and Delta Rule; 4.1 Introduction; 4.2 Operating Principle of the ADALINE; 4.3 Training Process of the ADALINE; 4.4 Comparison Between the Training Processes of the Perceptron and the ADALINE; 4.5 Exercises; 4.6 Practical Work; 5 Multilayer Perceptron Networks; 5.1 Introduction; 5.2 Operating Principle of the Multilayer Perceptron; 5.3 Training Process of the Multilayer Perceptron; 5.3.1 Deriving the Backpropagation Algorithm; 5.3.2 Implementing the Backpropagation Algorithm; 5.3.3 Optimized Versions of the Backpropagation Algorithm
• 5.4 Multilayer Perceptron Applications5.4.1 Problems of Pattern Classification; 5.4.2 Functional Approximation Problems (Curve Fitting); 5.4.3 Problems Involving Time-Variant Systems; 5.5 Aspects of Topological Specifications for MLP Networks; 5.5.1 Aspects of Cross-Validation Methods; 5.5.2 Aspects of the Training and Test Subsets; 5.5.3 Aspects of Overfitting and Underfitting Scenarios; 5.5.4 Aspects of Early Stopping; 5.5.5 Aspects of Convergence to Local Minima; 5.6 Implementation Aspects of Multilayer Perceptron Networks; 5.7 Exercises; 5.8 Practical Work 1 (Function Approximation)
• 5.9 Practical Work 2 (Pattern Classification)5.10 Practical Work 3 (Time-Variant Systems); 6 Radial Basis Function Networks; 6.1 Introduction; 6.2 Training Process of the RBF Network; 6.2.1 Adjustment of the Neurons from the Intermediate Layer (Stage I); 6.2.2 Adjustment of Neurons of the Output Layer (Stage II); 6.3 Applications of RBF Networks; 6.4 Exercises; 6.5 Practical Work 1 (Pattern Classification); 6.6 Practical Work 2 (Function Approximation); 7 Recurrent Hopfield Networks; 7.1 Introduction; 7.2 Operating Principles of the Hopfield Network