Systems Engineering Neural Networks

✍ Scribed by Alessandro Migliaccio, Giovanni Iannone

• Publisher: Wiley
• Year: 2023
• Tongue: English
• Leaves: 243
• Category: Library

✦ Synopsis

SYSTEMS ENGINEERING NEURAL NETWORKS

A complete and authoritative discussion of systems engineering and neural networks

In Systems Engineering Neural Networks, a team of distinguished researchers deliver a thorough exploration of the fundamental concepts underpinning the creation and improvement of neural networks with a systems engineering mindset. In the book, you’ll find a general theoretical discussion of both systems engineering and neural networks accompanied by coverage of relevant and specific topics, from deep learning fundamentals to sport business applications.

Readers will discover in-depth examples derived from many years of engineering experience, a comprehensive glossary with links to further reading, and supplementary online content. The authors have also included a variety of applications programmed in both Python 3 and Microsoft Excel.

The book provides:

• A thorough introduction to neural networks, introduced as key element of complex systems
• Practical discussions of systems engineering and forecasting, complexity theory and optimization and how these techniques can be used to support applications outside of the traditional AI domains
• Comprehensive explorations of input and output, hidden layers, and bias in neural networks, as well as activation functions, cost functions, and back-propagation
• Guidelines for software development incorporating neural networks with a systems engineering methodology

Perfect for students and professionals eager to incorporate machine learning techniques into their products and processes, Systems Engineering Neural Networks will also earn a place in the libraries of managers and researchers working in areas involving neural networks.

✦ Table of Contents

Cover
Title Page
Copyright
Contents
About the Authors
Acknowledgements
How to Read this Book
Part I Setting the Scene
Chapter 1 A Brief Introduction
1.1 The Systems Engineering Approach to Artificial Intelligence (AI)
1.2 Chapter Summary
Questions
Chapter 2 Defining a Neural Network
2.1 Biological Networks
2.2 From Biology to Mathematics
2.3 We Came a Full Circle
2.4 The Model of McCulloch‐Pitts
2.5 The Artificial Neuron of Rosenblatt
2.6 Final Remarks
2.7 Chapter Summary
Questions
Sources
Chapter 3 Engineering Neural Networks
3.1 A Brief Recap on Systems Engineering
3.2 The Keystone: SE4AI and AI4SE
3.3 Engineering Complexity
3.4 The Sport System
3.5 Engineering a Sports Club
3.6 Optimization
3.7 An Example of Decision Making
3.8 Futurism and Foresight
3.9 Qualitative to Quantitative
3.10 Fuzzy Thinking
3.11 It Is all in the Tools
3.12 Chapter Summary
Questions
Sources
Part II Neural Networks in Action
Chapter 4 Systems Thinking for Software Development
4.1 Programming Languages
4.2 One More Thing: Software Engineering
4.3 Chapter Summary
Questions
Source
Chapter 5 Practice Makes Perfect
5.1 Example 1: Cosine Function
5.2 Example 2: Corrosion on a Metal Structure
5.3 Example 3: Defining Roles of Athletes
5.4 Example 4: Athlete's Performance
5.5 Example 5: Team Performance
5.5.1 A Human‐Defined‐System
5.5.2 Human Factors
5.5.3 The Sports Team as System of Interest
5.5.4 Impact of Human Error on Sports Team Performance
5.5.4.1 Dataset
5.5.4.2 Problem Statement
5.5.4.3 Feature Engineering and Extraction
5.5.4.4 Creation of Computed Columns
5.5.4.5 Explorative Data Analysis (EDA)
5.5.4.6 Extension ‐ Sampling Method for an Imbalanced Dataset
5.5.4.7 Building a Neural Network Model
5.5.4.8 Training Outcome and Model Evaluation
5.5.4.9 Evaluate Using Test Data
5.6 Example 6: Trend Prediction
5.7 Example 7: Symplex and Game Theory
5.8 Example 8: Sorting Machine for Lego® Bricks
5.8.1 Challenge for Readers
Part III Down to the Basics
Chapter 6 Input/Output, Hidden Layer and Bias
6.1 Input/Output
6.2 Hidden Layer
6.2.1 How Many Hidden Nodes Should we Have?
6.3 Bias
6.4 Final Remarks
6.5 Chapter Summary
Questions
Source
Chapter 7 Activation Function
7.1 Types of Activation Functions
7.2 Activation Function Derivatives
7.3 Activation Functions Response to W and b Variables
7.4 Final Remarks
7.5 Chapter Summary
Questions
Source
Chapter 8 Cost Function, Back‐Propagation and Other Iterative Methods
8.1 What Is the Difference between Loss and Cost?
8.2 Training the Neural Network
8.3 Back‐Propagation (BP)
8.4 One More Thing: Gradient Method and Conjugate Gradient Method
8.5 One More Thing: Newton's Method
8.6 Chapter Summary
Questions
Sources
Chapter 9 Conclusions and Future Developments
Glossary and Insights
Index
EULA