The Applied Artificial Intelligence Workshop: Start working with AI today, to build games, design decision trees, and train your own machine learning models

Cover
FM
Copyright
Table of Contents
Preface
Chapter 1: Introduction to Artificial Intelligence
	Introduction
		How Does AI Solve Problems?
		Diversity of Disciplines in AI
	Fields and Applications of AI
		Simulation of Human Behavior
		Simulating Intelligence – the Turing Test
			What Disciplines Do We Need to Pass the Turing Test?
	AI Tools and Learning Models
		Intelligent Agents
	The Role of Python in AI
		Why Is Python Dominant in Machine Learning, Data Science, and AI?
		Anaconda in Python
		Python Libraries for AI
		A Brief Introduction to the NumPy Library
		Exercise 1.01: Matrix Operations Using NumPy
	Python for Game AI
		Intelligent Agents in Games
		Breadth First Search and Depth First Search
			Breadth First Search
			Depth First Search (DFS)
		Exploring the State Space of a Game
		Estimating the Number of Possible States in a Tic-Tac-Toe Game
		Exercise 1.02: Creating an AI with Random Behavior for the Tic-Tac-Toe Game
		Activity 1.01: Generating All Possible Sequences of Steps in a Tic-Tac-Toe Game
		Exercise 1.03: Teaching the Agent to Win
		Defending the AI against Losses
		Activity 1.02: Teaching the Agent to Realize Situations When It Defends Against Losses
		Activity 1.03: Fixing the First and Second Moves of the AI to Make It Invincible
	Heuristics
		Uninformed and Informed Searches
		Creating Heuristics
		Admissible and Non-Admissible Heuristics
		Heuristic Evaluation
			Heuristic 1: Simple Evaluation of the Endgame
			Heuristic 2: Utility of a Move
		Exercise 1.04: Tic-Tac-Toe Static Evaluation with a Heuristic Function
		Using Heuristics for an Informed Search
		Types of Heuristics
	Pathfinding with the A* Algorithm
		Exercise 1.05: Finding the Shortest Path Using BFS
	Introducing the A* Algorithm
		A* Search in Practice Using the simpleai Library
	Game AI with the Minmax Algorithm and Alpha-Beta Pruning
		Search Algorithms for Turn-Based Multiplayer Games
	The Minmax Algorithm
		Optimizing the Minmax Algorithm with Alpha-Beta Pruning
	DRYing Up the Minmax Algorithm – the NegaMax Algorithm
		Using the EasyAI Library
		Activity 1.04: Connect Four
	Summary
Chapter 2: An Introductionto Regression
	Introduction
	Linear Regression with One Variable
		Types of Regression
		Features and Labels
		Feature Scaling
		Splitting Data into Training and Testing
		Fitting a Model on Data with scikit-learn
		Linear Regression Using NumPy Arrays
		Fitting a Model Using NumPy Polyfit
			Plotting the Results in Python
		Predicting Values with Linear Regression
		Exercise 2.01: Predicting the Student Capacity of an Elementary School
	Linear Regression with Multiple Variables
		Multiple Linear Regression
		The Process of Linear Regression
		Importing Data from Data Sources
		Loading Stock Prices with Yahoo Finance
		Exercise 2.02: Using Quandl to Load Stock Prices
		Preparing Data for Prediction
		Exercise 2.03: Preparing the Quandl Data for Prediction
		Performing and Validating Linear Regression
		Predicting the Future
	Polynomial and Support Vector Regression
		Polynomial Regression with One Variable
		Exercise 2.04: First-, Second-, and Third-Degree Polynomial Regression
		Polynomial Regression with Multiple Variables
	Support Vector Regression
		Support Vector Machines with a 3-Degree Polynomial Kernel
		Activity 2.01: Boston House Price Prediction with Polynomial Regression of Degrees 1, 2, and 3 on Multiple Variables
	Summary
Chapter 3: An Introduction to Classification
	Introduction
	The Fundamentals of Classification
		Exercise 3.01: Predicting Risk of Credit Card Default (Loading the Dataset)
	Data Preprocessing
		Exercise 3.02: Applying Label Encoding to Transform Categorical Variables into Numerical variables
		Identifying Features and Labels
		Splitting Data into Training and Testing Using Scikit-Learn
	The K-Nearest Neighbors Classifier
		Introducing the K-Nearest Neighbors Algorithm (KNN)
		Distance Metrics With K-Nearest Neighbors Classifier in Scikit-Learn
			The Euclidean Distance
		The Manhattan/Hamming Distance
		Exercise 3.03: Illustrating the K-Nearest Neighbors Classifier Algorithm in Matplotlib
		Parameterization of the K-Nearest Neighbors Classifier in scikit-learn
		Exercise 3.04: K-Nearest Neighbors Classification in scikit-learn
		Activity 3.01: Increasing the Accuracy of Credit Scoring
	Classification with Support Vector Machines
		What Are Support Vector Machine Classifiers?
		Understanding Support Vector Machines
		Support Vector Machines in scikit-learn
		Parameters of the scikit-learn SVM
		Activity 3.02: Support Vector Machine Optimization in scikit-learn
	Summary
Chapter 4: An Introduction to Decision Trees
	Introduction
	Decision Trees
		Entropy
		Exercise 4.01: Calculating Entropy
		Information Gain
		Gini Impurity
		Exit Condition
		Building Decision Tree Classifiers Using scikit-learn
		Performance Metrics for Classifiers
		Exercise 4.02: Precision, Recall, and F1 Score Calculation
		Evaluating the Performance of Classifiers with scikit-learn
	The Confusion Matrix
		Activity 4.01: Car Data Classification
	Random Forest Classifier
		Random Forest Classification Using scikit-learn
		The Parameterization of the Random Forest Classifier
		Feature Importance
		Cross-Validation
		Extremely Randomized Trees
		Activity 4.02: Random Forest Classification for Your Car Rental Company
	Summary
Chapter 5: Artificial Intelligence: Clustering
	Introduction
	Defining the Clustering Problem
	Clustering Approaches
		Clustering Algorithms Supported by scikit-learn
	The K-Means Algorithm
		Exercise 5.01: Implementing K-Means in scikit-learn
		The Parameterization of the K-Means Algorithm in scikit-learn
		Exercise 5.02: Retrieving the Center Points and the Labels
		K-Means Clustering of Sales Data
		Activity 5.01: Clustering Sales Data Using K-Means
	The Mean Shift Algorithm
		Exercise 5.03: Implementing the Mean Shift Algorithm
		The Mean Shift Algorithm in scikit-learn
		Hierarchical Clustering
		Agglomerative Hierarchical Clustering in scikit-learn
	Clustering Performance Evaluation
		The Adjusted Rand Index
		The Adjusted Mutual Information
		The V-Measure, Homogeneity, and Completeness
		The Fowlkes-Mallows Score
		The Contingency Matrix
		The Silhouette Coefficient
		The Calinski-Harabasz Index
		The Davies-Bouldin Index
		Activity 5.02: Clustering Red Wine Data Using the Mean Shift Algorithm and Agglomerative Hierarchical Clustering
	Summary
Chapter 6: Neural Networks and Deep Learning
	Introduction
	Artificial Neurons
	Neurons in TensorFlow
		Exercise 6.01: Using Basic Operations and TensorFlow Constants
	Neural Network Architecture
		Weights
		Biases
		Use Cases for ANNs
	Activation Functions
		Sigmoid
		Tanh
		ReLU
		Softmax
		Exercise 6.02: Activation Functions
	Forward Propagation and the Loss Function
	Backpropagation
	Optimizers and the Learning Rate
		Exercise 6.03: Classifying Credit Approval
	Regularization
		Exercise 6.04: Predicting Boston House Prices with Regularization
		Activity 6.01: Finding the Best Accuracy Score for the Digits Dataset
	Deep Learning
		Shallow versus Deep Networks
	Computer Vision and Image Classification
		Convolutional Neural Networks (CNNs)
		Convolutional Operations
		Pooling Layer
		CNN Architecture
		Activity 6.02: Evaluating a Fashion Image Recognition Model Using CNNs
	Recurrent Neural Networks (RNNs)
		RNN Layers
		The GRU Layer
		The LSTM Layer
		Activity 6.03: Evaluating a Yahoo Stock Model with an RNN
		Hardware for Deep Learning
		Challenges and Future Trends
	Summary
Appendix
Index