Lessons 1: Preface

Lessons 2: What Is Artificial Intelligence?

• What Is Intelligence?
• Testing Machine Intelligence
• The General Problem Solver
• Strong and Weak Artificial Intelligence
• Artificial Intelligence Planning
• Learning over Memorising

Lessons 3: The Rise of Machine Learning

• Practical Applications of Machine Learning
• Artificial Neural Networks
• The Fall and Rise of the Perceptron
• Big Data Arrives

Lessons 4: Zeroing in on the Best Approach

• Expert System Versus Machine Learning
• Supervised Versus Unsupervised Learning
• Backpropagation of Errors
• Regression Analysis

Lessons 5: Common AI Applications

• Intelligent Robots
• Natural Language Processing
• The Internet of Things

Lessons 6: Putting AI to Work on Big Data

• Understanding the Concept of Big Data
• Teaming Up with a Data Scientist
• Machine Learning and Data Mining: What’s the Difference?
• Making the Leap from Data Mining to Machine Learning
• Taking the Right Approach

Lessons 7: Weighing Your Options

Lessons 8: What Is Machine Learning?

• How a Machine Learns
• Working with Data
• Applying Machine Learning
• Different Types of Learning

Lessons 9: Different Ways a Machine Learns

• Supervised Machine Learning
• Unsupervised Machine Learning
• Semi-Supervised Machine Learning
• Reinforcement Learning

Lessons 10: Popular Machine Learning Algorithms

• Decision Trees
• k-Nearest Neighbour
• k-Means Clustering
• Regression Analysis
• Näive Bayes

Lessons 11: Applying Machine Learning Algorithms

• Fitting the Model to Your Data
• Choosing Algorithms
• Ensemble Modeling
• Deciding on a Machine Learning Approach

Lessons 12: Words of Advice

• Start Asking Questions
• Don’t Mix Training Data with Test Data
• Don’t Overstate a Model’s Accuracy
• Know Your Algorithms

Lessons 13: What Are Artificial Neural Networks?

• Why the Brain Analogy?
• Just Another Amazing Algorithm
• Getting to Know the Perceptron
• Squeezing Down a Sigmoid Neuron
• Adding Bias

Lessons 14: Artificial Neural Networks in Action

• Feeding Data into the Network
• What Goes on in the Hidden Layers
• Understanding Activation Functions
• Adding Weights
• Adding Bias

Lessons 15: Letting Your Network Learn

• Starting with Random Weights and Biases
• Making Your Network Pay for Its Mistakes: The Cost Function
• Combining the Cost Function with Gradient Descent
• Using Backpropagation to Correct for Errors
• Tuning Your Network
• Employing the Chain Rule
• Batching the Data Set with Stochastic Gradient Descent

Lessons 16: Using Neural Networks to Classify or Cluster

• Solving Classification Problems
• Solving Clustering Problems

Lessons 17: Key Challenges

• Obtaining Enough Quality Data
• Keeping Training and Test Data Separate
• Carefully Choosing Your Training Data
• Taking an Exploratory Approach
• Choosing the Right Tool for the Job

Lessons 18: Harnessing the Power of Natural Language Processing

• Extracting Meaning from Text and Speech with NLU
• Delivering Sensible Responses with NLG
• Automating Customer Service
• Reviewing the Top NLP Tools and Resources

Lessons 19: Automating Customer Interactions

• Choosing Natural Language Technologies
• Review the Top Tools for Creating Chatbots and Virtual Agents

Lessons 20: Improving Data-Based Decision-Making

• Choosing Between Automated and Intuitive Decision-Making
• Gathering Data in Real Time from IoT Devices
• Reviewing Automated Decision-Making Tools

Lessons 21: Using Machine Learning to Predict Events and Outcomes

• Machine Learning Is Really about Labeling Data
• Looking at What Machine Learning Can Do
• Use Your Power for Good, Not Evil: Machine Learning Ethics
• Review the Top Machine Learning Tools

Lessons 22: Building Artificial Minds

• Separating Intelligence from Automation
• Adding Layers for Deep Learning
• Considering Applications for Artificial Neural Networks
• Reviewing the Top Deep Learning Tools

The Rise of Machine Learning

• Analysing the Artificial Intelligence, Machine Learning, and Deep Learning
• Analysing the Similarities and Differences between Intelligence, Machine Learning and Deep Learning.

Putting AI to Work on Big Data

• Understanding Concepts Used to Automate Decision-Making Processes

Weighing Your Options

• Understanding Approaches Used to Automate Computer Decision-Making Processes

Popular Machine Learning Algorithms

• Analysing Algorithms to Parse and Analyse Data
• Identifying Algorithms to Parse and Analyse Data
• Summarising Algorithms to Parse and Analyse Data

Using Neural Networks to Classify or Cluster

• Summarising Methods Used to Automate Computer Decision-Making Processes