Practical Artificial Intelligence (eBook)

Arnaldo Pérez Castaño is a computer scientist based in Cuba. He’s the author of PrestaShop Recipes (Apress, 2017) and a series of programming books—JavaScript Fácil, HTML y CSS Fácil, and Python Fácil (Marcombo S.A.)—and writes AI related articles for MSDN Magazine, VisualStudioMagazine.com, and Smashing Magazine. He is one of the co-founders of Havana Digital Enterprises and the creator of their first websites, http://www.havanaclassiccartour.com and www.havanadanceclass.com. His expertise includes Visual Basic, C#, .NET Framework and Artificial Intelligence.  Arnaldo offers his services through freelancer.com and served as reviewer for the Journal of Mathematical Modelling and Algorithms in Operations Research. Cinema and music are some of his passions.

Table of Contents 5
About the Author 12
About the Technical Reviewer 13
Acknowledgments 14
Introduction 15
Chapter 1: Logic & AI
What Is Logic? 19
Propositional Logic 20
Logical Connectives 23
Negation 24
Conjunction 25
Disjunction 26
Implication 27
Equivalence 28
Laws of Propositional Logic 29
Normal Forms 33
Logic Circuits 34
Practical Problem: Using Inheritance and  C# Operators to Evaluate Logic Formulas 38
Practical Problem: Representing Logic Formulas as Binary Decision Trees 43
Practical Problem: Transforming a Formula into Negation Normal Form (NNF) 48
Practical Problem: Transforming a Formula into Conjunctive Normal Form (CNF) 53
Summary 57
Chapter 2: Automated Theorem Proving & First-Order Logic
Automated Theorem Proving 59
Practical Problem: Clauses and CNFs Classes in C# 62
DPLL Algorithm 72
Practical Problem: Modeling the Pigeonhole Principle in Propositional Logic 84
Practical Problem: Finding Whether a Propositional Logic Formula is SAT 85
First-Order Logic 92
Predicates in C# 97
Practical Problem: Cleaning Robot 99
Summary 106
Chapter 3: Agents 107
What’s an Agent? 108
Agent Properties 111
Types of Environments 115
Agents with State 118
Practical Problem: Modeling the Cleaning Robot as an Agent and Adding State to It 119
Agent Architectures 129
Reactive Architectures: Subsumption Architecture 130
Deliberative Architectures: BDI Architecture 135
Hybrid Architectures 143
Touring Machines 147
InteRRaP 149
Summary 151
Chapter 4: Mars Rover 152
What’s a Mars Rover? 153
Mars Rover Architecture 155
Mars Rover Code 158
Mars Rover Visual Application 191
Summary 207
Chapter 5: Multi-Agent Systems 208
What’s a Multi-Agent System? 209
Multi-Agent Organization 212
Communication 214
Speech Act Theory 216
Agent Communication Languages (ACL) 219
Coordination & Cooperation
Negotiation Using Contract Net 230
Social Norms & Societies
Summary 235
Chapter 6: Communication in a Multi-Agent System Using WCF 236
Services 237
Contracts 239
Bindings 242
Endpoints 244
Publisher/Subscriber Pattern 245
Practical Problem: Communicating Among Multiple Agents Using WCF 246
Summary 263
Chapter 7: Cleaning Agents: A Multi-Agent System Problem 264
Program Structure 265
Cleaning Task 266
Cleaning Agent Platform 269
Contract Net 271
FIPA-ACL 277
MAS Cleaning Agent 282
GUI 295
Running the Application 298
Summary 303
Chapter 8: Simulation 304
What Is Simulation? 305
Discrete-Event Simulation 307
Probabilistic Distributions 309
Practical Problem: Airport Simulation 312
Summary 328
Chapter 9: Support Vector Machines 329
What Is a Support Vector Machine (SVM)? 332
Practical Problem: Linear SVM in C# 342
Imperfect Separation 357
Non-linearly Separable Case: Kernel Trick 359
Sequential Minimal Optimization Algorithm (SMO) 362
Practical Problem: SMO Implementation 370
Summary 379
Chapter 10: Decision Trees 380
What Is a Decision Tree? 381
Generating a Decision Tree: ID3 Algorithm 385
Entropy and Information Gain 388
Practical Problem: Implementing the ID3 Algorithm 390
C4.5 Algorithm 406
Practical Problem: Implementing the C4.5 Algorithm 412
Summary 423
Chapter 11: Neural Networks 424
What Is a Neural Network? 425
Perceptron: Singular NN 428
Practical Problem: Implementing the Perceptron NN 433
Adaline & Gradient Descent Search
Stochastic Approximation 444
Practical Problem: Implementing Adaline NN 445
Multi-layer Networks 448
Backpropagation Algorithm 453
Practical Problem: Implementing Backpropagation & Solving the XOR Problem
Summary 472
Chapter 12: Handwritten Digit Recognition 474
What Is Handwritten Digit Recognition? 475
Training Data Set 477
Multi-layer NN for HDR 477
Implementation 480
Testing 489
Summary 491
Chapter 13: Clustering & Multi-objective Clustering
What Is Clustering? 493
Hierarchical Clustering 497
Partitional Clustering 499
Practical Problem: K-Means Algorithm 503
Multi-objective Clustering 512
Pareto Frontier Builder 514
Summary 520
Chapter 14: Heuristics & Metaheuristics
What Is a Heuristic? 522
Hill Climbing 524
Practical Problem: Implementing Hill Climbing 527
P-Metaheuristics: Genetic Algorithms 534
Practical Problem: Implementing a Genetic Algorithm for the Traveling Salesman Problem 538
S-Metaheuristics: Tabu Search 550
Summary 560
Chapter 15: Game Programming 561
What Is a Video Game? 563
Searching in Games 565
Uninformed Search 568
Practical Problem: Implementing BFS, DFS, DLS, and IDS 572
Practical Problem: Implementing Bidirectional Search on the Sliding Tiles Puzzle 580
Informed Search 592
A* for the Sliding Tiles Puzzle 595
Summary 600
Chapter 16: Game Theory: Adversarial Search & Othello Game
What Is Game Theory? 602
Adversarial Search 605
Minimax Search Algorithm 608
Alpha-Beta Pruning 611
Othello Game 614
Practical Problem: Implementing the Othello Game in Windows Forms 619
Practical Problem: Implementing the Othello Game AI Using Minimax 640
Summary 643
Chapter 17: Reinforcement Learning 644
What Is Reinforcement Learning? 645
Markov Decision Process 647
Value/Action–Value Functions & Policies
Value Iteration Algorithm 655
Policy Iteration Algorithm 657
Q-Learning & Temporal Difference
Practical Problem: Solving a Maze Using Q-Learning 661
Summary 679
Index 680