Book description
The utility of artificial neural network models lies in the fact that they can be used to infer functions from observations—making them especially useful in applications where the complexity of data or tasks makes the design of such functions by hand impractical.
Exploring Neural Networks with C# presents the important properties of neural networks—while keeping the complex mathematics to a minimum. Explaining how to build and use neural networks, it presents complicated information about neural networks structure, functioning, and learning in a manner that is easy to understand.
Taking a "learn by doing" approach, the book is filled with illustrations to guide you through the mystery of neural networks. Examples of experiments are provided in the text to encourage individual research. Online access to C# programs is also provided to help you discover the properties of neural networks.
Following the procedures and using the programs included with the book will allow you to learn how to work with neural networks and evaluate your progress. You can download the programs as both executable applications and C# source code from http://home.agh.edu.pl/~tad//index.php?page=programy&lang=en
Table of contents
 Foreword
 Preface
 Acknowledgments

Chapter 1  Introduction to Natural and Artificial Neural Networks
 1.1 Why Learn about Neural Networks?
 1.2 From Brain Research to Artificial Neural Networks
 1.3 Construction of First Neural Networks
 1.4 Layered Construction of Neural Network
 1.5 From Biological Brain to First Artificial Neural Network
 1.6 Current Brain Research Methods
 1.7 Using Neural Networks to Study the Human Mind
 1.8 Simplification of Neural Networks: Comparison with Biological Networks
 1.9 Main Advantages of Neural Networks
 1.10 Neural Networks as Replacements for Traditional Computers
 1.11 Working with Neural Networks
 References

Chapter 2  Neural Net Structure
 2.1 Building Neural Nets
 2.2 Constructing Artificial Neurons
 2.3 Attempts to Model Biological Neurons
 2.4 How Artificial Neural Networks Work
 2.5 Impact of Neural Network Structure on Capabilities
 2.6 Choosing Neural Network Structures Wisely
 2.7 “Feeding” Neural Networks: Input Layers
 2.8 Nature of Data: The Home of the Cow
 2.9 Interpreting Answers Generated by Networks: Output Layers
 2.10 Preferred Result: Number or Decision?
 2.11 Network Choices: One Network with Multiple Outputs versus Multiple Networks with Single Outputs
 2.12 Hidden Layers
 2.13 Determining Numbers of Neurons
 References
 Questions and SelfStudy Tasks

Chapter 3  Teaching Networks
 3.1 Network Tutoring
 3.2 SelfLearning
 3.3 Methods of Gathering Information
 3.4 Organizing Network Learning
 3.5 Learning Failures
 3.6 Use of Momentum
 3.8 Duration of Learning Process
 3.9 Teaching Hidden Layers
 3.10 Learning without Teachers
 3.11 Cautions Surrounding SelfLearning
 Questions and SelfStudy Tasks

Chapter 4  Functioning of Simplest Networks
 4.1 From Theory to Practice: Using Neural Networks
 4.2 Capacity of Single Neuron
 4.3 Experimental Observations
 4.4 Managing More Inputs
 4.5 Network Functioning
 4.6 Construction of Simple Linear Neural Network
 4.7 Use of Network
 4.8 Rivalry in Neural Networks
 4.9 Additional Applications
 Questions and SelfStudy Tasks
 Chapter 5  Teaching Simple Linear OneLayer Neural Networks

Chapter 6  Nonlinear Networks
 6.1 Advantages of Nonlinearity
 6.2 Functioning of Nonlinear Neurons
 6.3 Teaching Nonlinear Networks
 6.4 Demonstrating Actions of Nonlinear Neurons
 6.5 Capabilities of Multilayer Networks of Nonlinear Neurons
 6.6 Nonlinear Neuron Learning Sequence
 6.7 Experimentation during Learning Phase
 Questions and SelfStudy Tasks

Chapter 7  Backpropagation
 7.1 Definition
 7.2 Changing Thresholds of Nonlinear Characteristics
 7.3 Shapes of Nonlinear Characteristics
 7.4 Functioning of Multilayer Network Constructed of Nonlinear Elements
 7.5 Teaching Multilayer Networks
 7.6 Observations during Teaching
 7.7 Reviewing Teaching Results
 Questions and SelfStudy Tasks
 Chapter 8  Forms of Neural Network Learning

Chapter 9  SelfLearning Neural Networks
 9.1 Basic Concepts
 9.2 Observation of Learning Processes
 9.3 Evaluating Progress of SelfTeaching
 9.4 Neuron Responses to SelfTeaching
 9.5 Imagination and Improvisation
 9.6 Remembering and Forgetting
 9.7 SelfLearning Triggers
 9.8 Benefits from Competition
 9.9 Results of SelfLearning with Competition
 Questions and SelfStudy Tasks

Chapter 10  SelfOrganizing Neural Networks
 10.1 Structure of Neural Network to Create Mappings Resulting from SelfOrganizing
 10.2 Uses of SelfOrganization
 10.3 Implementing Neighborhood in Networks
 10.4 Neighbor Neurons
 10.5 Uses of Kohonen Networks
 10.6 Kohonen Network Handling of Difficult Data
 10.7 Networks with Excessively Wide Ranges of Initial Weights
 10.8 Changing SelfOrganization via SelfLearning
 10.9 Practical Uses of Kohonen Networks
 10.10 Tool for Transformation of Input Space Dimensions
 Questions and SelfStudy Tasks

Chapter 11  Recurrent Networks
 11.1 Description of Recurrent Neural Network
 11.2 Features of Networks with Feedback
 11.3 Benefits of Associative Memory
 11.4 Construction of Hopfield Network
 11.5 Functioning of Neural Network as Associative Memory
 11.6 Program for Examining Hopfield Network Operations
 11.7 Interesting Examples
 11.8 Automatic Pattern Generation for Hopfield Network
 11.9 Studies of Associative Memory
 11.10 Other Observations of Associative Memory
 Questions and SelfStudy Tasks
Product information
 Title: Exploring Neural Networks with C#
 Author(s):
 Release date: September 2014
 Publisher(s): CRC Press
 ISBN: 9781482233407
You might also like
book
Guide to Essential Math, 2nd Edition
This book reminds students in junior, senior and graduate level courses in physics, chemistry and engineering …
book
HandsOn Machine Learning with ScikitLearn, Keras, and TensorFlow, 2nd Edition
Through a series of recent breakthroughs, deep learning has boosted the entire field of machine learning. …
book
Practical Statistics for Data Scientists, 2nd Edition
Statistical methods are a key part of data science, yet few data scientists have formal statistical …
book
40 Algorithms Every Programmer Should Know
Learn algorithms for solving classic computer science problems with this concise guide covering everything from fundamental …