Artificial Intelligence Driven by Machine Learning and Deep Learning

✍ Scribed by Bahman Zohuri, Siamak Zadeh

• Publisher: Nova Science Pub Inc
• Year: 2020
• Tongue: English
• Leaves: 457
• Category: Library

✦ Synopsis

"The future of any business from banking, e-commerce, real estate, homeland security, healthcare, marketing, the stock market, manufacturing, education, retail to government organizations depends on the data and analytics capabilities that are built and scaled. The speed of change in technology in recent years has been a real challenge for all businesses. To manage that, a significant number of organizations are exploring the BigData (BD) infrastructure that helps them to take advantage of new opportunities while saving costs. Timely transformation of information is also critical for the survivability of an organization. Having the right information at the right time will enhance not only the knowledge of stakeholders within an organization but also providing them with a tool to make the right decision at the right moment. It is no longer enough to rely on a sampling of information about the organizations' customers. The decision-makers need to get vital insights into the customers' actual behavior, which requires enormous volumes of data to be processed. We believe that Big Data infrastructure is the key to successful Artificial Intelligence (AI) deployments and accurate, unbiased real-time insights. Big data solutions have a direct impact and changing the way the organization needs to work with help from AI and its components ML and DL. In this article, we discuss these topics"--

✦ Table of Contents

Contents
Preface
Acknowledgment
Chapter 1
Artificial Intelligence
1.1. Introduction
1.2. History of Artificial Intelligence
1.3. Weak Artificial Intelligence (WAI)
1.3.1. And It Is Indeed a Possibility. The Signs Are All There
1.3.2. Technological Singularity
1.4. Artificial General Intelligence (AGI)
1.4.1. Existential Risk from Artificial General Intelligence
1.5. Natural Language Processing (NLP)
1.5.1. How Does NLP Work?
1.6. Cognitive Science and Cognitive Linguistics
1.7. Big Data
1.7.1. Big Data History and Current Considerations
1.7.2. What Are Big Data and Big Data Analytics?
1.7.3. Why Is Big Data Important?
1.7.4. Where Big Data Is Used and Who Uses it
1.7.5. How Does Big Data Work
References
Chapter 2
Machine Learning
2.1. Introduction
2.2. Problem Solving with Machine Learning
2.3. Estimating Probability Distributions
2.4. Linear Classifiers and Perceptron Algorithm
2.5. Decision Trees and Model Selection
2.6. Random Forest and How Does It Work
2.7. Overfitting in Decision Trees
2.8. Learning with Kernel Machines and Support Vector Machines
2.9. Debugging and Improving Machine Learning
2.10. Machine Learning Logistic (MLL)
2.11. Why Machine Learning
2.12. Machine Learning Boosting eCommerce
2.12.1. Eight Significant Applications of Machine Learning in eCommerce
2.12.2. Conclusion of Machine Learning and eCommerce
References
Chapter 3
Deep Learning
3.1. Introduction
3.2. Neural Networks Three Classes (MLP, CNN and RNN)
3.2.1. Multi-Layer Perceptrons (MLPs)
3.2.1.1. When to Use Multi-Layer Perceptrons (MLPs)?
3.2.2. Convolutional Neural Networks (CNNs)
3.2.2.1. When to Use Convolutional Neural Networks (CNNs)?
3.2.3. Recurrent Neural Networks (RNNs)
3.2.3.1. Cardinality from Timesteps (Not Features!)
3.2.3.2. Two Common Misunderstandings by Practitioners
3.3. Neural Networks Prospect
3.4. Deep Learning and Neural Networks
3.5. Hybrid Network Models
3.6. Deep Learning versus Machine Learning
3.7. Deep Learning Limitation
3.7.1. Local Generalization versus Generalization
3.8. Summary
3.9. The Future of Deep Learning
3.9.1. Models as Programs
3.9.2. Beyond Backpropagation and Differential Layers
3.9.3. Automated Machine Learning
3.9.4. Lifelong Learning and Modular Subroutine Reuse
3.9.5. In Summary and the Long-Term Vision
References
Chapter 4
Neural Networks Concepts
4.1. Introduction
4.2. Artificial Neural Network (ANN)
4.2.1. Artificial Neuron with Continuous Characteristics
4.2.2. Single-Layer Network
4.2.3. Multilayer Network
4.2.4. Learning Process
4.3. Back-Propagation Neural Networks
4.3.1. Linear Separability and the XOR Problem
4.3.2. The Architecture of Backpropagation Networks
4.3.3. Back Propagation Processing Unit
4.3.4. Back Propagation Learning Algorithm
4.3.5. Local Minimum Problem
4.3.6. Generalization
4.4. Biological Background
4.5. Biological Neural Networks
4.6. Learning in a Neural Network
4.6.1. The Pattern Associator
4.6.2. The Hebb Rule
4.6.3. The Delta Rule
4.6.4. The Generalized Delta Rule
4.7. Fuzzy Logic and Neural Networks
Summary and Conclusion
References
Chapter 5
Artificial Intelligence, Machine Learning and Deep Learning
5.1. Introduction
5.2. How Deep Learning Functions and Works
5.2.1. Neural Networks Driving Deep Learning
5.2.2. Recurrent Neural Networks
5.2.3. Recurrent Neural Networks Application/Usage
5.3. Long Short Term Memory (LSTM)
5.4. Machine Learning Application Driving Business Problems
5.4.1. What Kinds of Business Problems Can Machine Learning Handle
5.4.1.1. Machine Learning in Finance and Banking Industry
5.4.1.2. Machine Learning in Marketing Industry
5.4.1.3. Machine Learning in Healthcare Industry
5.4.1.4. Machine Learning in Manufacturing and Robotics Industry
5.5. Risk and Future Outlook of Machine Learning
5.6. Glossary of Robotics-Related Machine Learning Concepts
References
Chapter 6
Internet of Things (IoT)
6.1. Introduction
6.2. Artificial Intelligence Powering Internet of Things for Data Collection
6.2.1. Convergence with Big Data
6.2.2. More Industrial Use of IoT
6.2.3. Decentralization Efforts Using Blockchain
6.2.4. The Rising Trend of Smart Cities
6.2.5. Better Router Security to Prevent User Data Being Hacked
6.2.6. More Appliances on the IoT than People
6.2.7. Section Conclusion
6.3. Internet of Things Driving Industries
6.3.1. Internet of Things Driving Retailers Today
6.4. Consumer Internet of Things (CIoT) Definition
6.5. Key Characteristics of Internet of Things
6.6. The Longer Internet of Things Definition
References
Chapter 7
Energy Driven by Internet of Things Analytics and Artificial Intelligence
7.1. Introduction
7.2. Securing Utilities against Cyberattacks
7.3. Modern Threats Driving Modern Cyberattacks
7.4. Industrial Control Systems (ICS) Security Guideline
7.4.1. Overview of Industrial Control Systems (ICS)
7.4.2. Overview of SCAD, DCS and PLCs
7.4.3. Industrial Control System (ICS) Operation
7.4.4. Key Industrial Control Systems (ICS) Components
7.4.5. Control Components
7.4.6. Network Components
7.5. Supervisory Control and Data Acquisition (SCADA) Systems
7.6. Distributed Control Systems (DCS)
7.7. Programmable Logic Controllers (PLC)
7.8. Artificial Intelligence Driving Modern Protections against Modern Threats
7.9. Artificial Intelligence and Cyber Security
References
Chapter 8
Artificial Intelligence Driven Image Processing
8.1. Introduction
8.2. Image Processing Methods, Techniques, and Tools
8.3. Machine Learning Frameworks and Platforms for Image Processing
8.4. Using Neural Networks for Image Processing
Conclusion
References
Chapter 9
Python Programming Driven Artificial Intelligence
9.1. Introduction
9.2. Getting Started with Python
9.3. Programming with Python
9.4. Python Basics
9.4.1. Programming in IDLE
9.4.2. Data Types in Python
9.5. Python Standard and Add-on Libraries
9.5.1. Pandas
9.5.2. NumPy
9.5.3. Matplotlib
9.5.4. SciPy
9.5.5. Seaborn
9.5.6. Statsmodels
9.5.7. Scikit-Lear
9.5.8. TensorFlow
9.5.9. Keras
9.6. Python for Artificial Intelligence, Machine Learning, and Deep Learning
9.7. Further Reading
References
Chapter 10
From Business Intelligence to Artificial Intelligence
10.1. Introduction
10.2. What Is Business Intelligence (BI)
10.3. What Is Artificial Intelligence (AI)
10.4. AI versus BI: Difference and Synergies
10.5. Integration of Business Intelligence with Artificial Intelligence
10.6. Artificial Intelligence is the Future of Business Intelligence
Conclusion
References
Appendix A: Basic Glossary of Artificial Intelligence, Machine Leaning and Deep Learning
A.1. Basic Glossary Lists
A.2. Glossary of Machine Learning Terms
A.3. Glossary of Industrial Control Systems (ICS) Terms
Appendix B: Online Robotics, Industrial Automation, Robots and Unmanned Vehicles
B1. Introduction
B2. What Is Robot Vision?
B3. Robot Vision's Family Tree
B.3.1. Signal Processing
B.3.2. Image Processing vs Computer Vision
B.3.3. Pattern Recognition and Machine Learning
B.3.4. Machine Vision
B.3.5. Robot Vision
B.4. What You Put in vs What You Get out
References
Appendix C: Backpropagation through Time (BPTT)
C.1. Introduction
C.2. Backpropagation Training Algorithm
C.3. Summary
References
Appendix D: An Introduction to Sequence Prediction
D.1. Introduction
D.2. Primer About Sequence Prediction
D.3. Current Landscape of Solutions
D.4. Enter Compact Prediction Tree (CPT)
D.5. Understanding the Data Structure in (CPT)
D.6. Understanding How Training and Prediction Works in CPT
D.6.1. Training Phase
D.6.2. Prediction Phase
D.7. Creating Model and Making Predictions
D.8. The Data Mining and Summary of an Introduction to Sequence Prediction
D.8.1. What Is a Sequence
D.8.2. What Is Sequence Prediction
D.8.3. How to Determine if a Sequence Prediction Model Is Good
References
Appendix E: Kernel Principle Components Analysis
E.1. Introduction
E.2. Centering Data in Feature Space
E.3. Background in Linear Principal Component Analysis (PCA)
E.4. Large Datasets
E.5. Applications
References
Appendix F: Elasticsearch
F.1. Introduction
F.2. Features
F.3. How Does Elasticsearch Work?
F.4. The Elasticsearch Indexing
F.5. How Elasticsearch Represents Data
F.6. Query DSL
F.7. The Elastic Stack
F.8. Elasticsearch Use Cases
F.9. Cisco Commerce Delivery Platform
F.9.1. Cisco Threat Intelligence Department
Conclusion
References
About the Authors
Index
Blank Page