This book explains how a computer, by replicating the processes of Darwinian evolution, taught itself to play checkers far better than its creators could have programmed it to play. Fogel (editor, IEEE Transactions on Evolutionary Computation) considers the implications for evolutionary computations and artificial intelligence. Diagrams illustrate the evolutionary and computational processes at work, and the course of various games of checkers. Annotation copyrighted by Book News, Inc., Portland, OR.

It’s hard to believe that it’s been over a decade since One Jump Ahead: Challenging Human Supremacy at Checkers was published. I’m delighted to have the oppor- nity to update and expand the book. The ?rst edition ended on a sad note and that was re?ected in the writing. It is now eleven years later and the project has come to a satisfying conclusion. Since its inception, the checkers project has consumed eighteen years of my life— twenty if you count the pre-CHINOOK and post-solving work. It’s hard for me to believe that I actually stuck with it for that long. My wife, Steph, would probably have something witty to say about my obsessive behavior. Rereading the book after a decade was dif?cult for me. When I originally wrote One Jump Ahead, I vowed to be candid in my telling of the story. That meant being honest about what went right and what went wrong. I have been criticized for being hard on some of the characters. That may be so, but I hope everyone will agree that the person receiving the most criticism was, justi?ably, me. I tried to be balanced in the storytelling, re?ecting things as they really happened and not as some sanitized everyone-lived-happily-ever-after tale.

This book was written to support Eurisko, an advanced math and computer science elective course sequence within the Math Academy program at Pasadena High School. During its operation from 2020 to 2023, Eurisko was the most advanced high school math/CS sequence in the USA. It culminated in high school students doing masters/PhD-level coursework (reproducing academic research papers in artificial intelligence, building everything from scratch in Python). CONTENTS 1. HELLO WORLD - Some Short Introductory Coding Exercises; Converting Between Binary, Decimal, and Hexadecimal; Recursive Sequences; Simulating Coin Flips; Roulette Wheel Selection; Cartesian Product. 2. SEARCHING AND SORTING - Brute Force Search with Linear-Encoding Cryptography; Solving Magic Squares via Backtracking; Estimating Roots via Bisection Search and Newton-Raphson Method; Single-Variable Gradient Descent; Multivariable Gradient Descent; Selection, Bubble, Insertion, and Counting Sort; Merge Sort and Quicksort. 3. OBJECTS - Basic Matrix Arithmetic; Reduced Row Echelon Form and Applications to Matrix Arithmetic; K-Means Clustering; Tic-Tac-Toe and Connect Four; Euler Estimation; SIR Model for the Spread of Disease; Hodgkin-Huxley Model of Action Potentials in Neurons; Hash Tables; Simplex Method. 4. REGRESSION AND CLASSIFICATION - Linear, Polynomial, and Multiple Linear Regression via Pseudoinverse; Regressing a Linear Combination of Nonlinear Functions via Pseudoinverse; Power, Exponential, and Logistic Regression via Pseudoinverse; Overfitting, Underfitting, Cross-Validation, and the Bias-Variance Tradeoff; Regression via Gradient Descent; Multiple Regression and Interaction Terms; K-Nearest Neighbors; Naive Bayes. 5. GRAPHS - Breadth-First and Depth-First Traversals; Distance and Shortest Paths in Unweighted Graphs; Dijkstra's Algorithm for Distance and Shortest Paths in Weighted Graphs; Decision Trees; Introduction to Neural Network Regressors; Backpropagation. 6. GAMES - Canonical and Reduced Game Trees for Tic-Tac-Toe; Minimax Strategy; Reduced Search Depth and Heuristic Evaluation for Connect Four; Introduction to Blondie24 and Neuroevolution; Reimplementing Fogel's Tic-Tac-Toe Paper; Reimplementing Blondie24; Reimplementing Blondie24: Convolutional Version.

Provides an in-depth and even treatment of the three pillars of computational intelligence and how they relate to one another This book covers the three fundamental topics that form the basis of computational intelligence: neural networks, fuzzy systems, and evolutionary computation. The text focuses on inspiration, design, theory, and practical aspects of implementing procedures to solve real-world problems. While other books in the three fields that comprise computational intelligence are written by specialists in one discipline, this book is co-written by current former Editor-in-Chief of IEEE Transactions on Neural Networks and Learning Systems, a former Editor-in-Chief of IEEE Transactions on Fuzzy Systems, and the founding Editor-in-Chief of IEEE Transactions on Evolutionary Computation. The coverage across the three topics is both uniform and consistent in style and notation. Discusses single-layer and multilayer neural networks, radial-basis function networks, and recurrent neural networks Covers fuzzy set theory, fuzzy relations, fuzzy logic interference, fuzzy clustering and classification, fuzzy measures and fuzzy integrals Examines evolutionary optimization, evolutionary learning and problem solving, and collective intelligence Includes end-of-chapter practice problems that will help readers apply methods and techniques to real-world problems Fundamentals of Computational intelligence is written for advanced undergraduates, graduate students, and practitioners in electrical and computer engineering, computer science, and other engineering disciplines.

Evolution is Nature’s design process. The natural world is full of wonderful examples of its successes, from engineering design feats such as powered flight, to the design of complex optical systems such as the mammalian eye, to the merely stunningly beautiful designs of orchids or birds of paradise. With increasing computational power, we are now able to simulate this process with greater fidelity, combining complex simulations with high-performance evolutionary algorithms to tackle problems that used to be impractical. This book showcases the state of the art in evolutionary algorithms for design. The chapters are organized by experts in the following fields: evolutionary design and "intelligent design" in biology, art, computational embryogeny, and engineering. The book will be of interest to researchers, practitioners and graduate students in natural computing, engineering design, biology and the creative arts.

The book is focused on the developments and prospective challenging problems in the area of mind game playing (i.e. playing games that require mental skills) using Computational Intelligence (CI) methods, mainly neural networks, genetic/evolutionary programming and reinforcement learning. The majority of discussed game playing ideas were selected based on their functional similarity to human game playing. These similarities include: learning from scratch, autonomous experience-based improvement and example-based learning. The above features determine the major distinction between CI and traditional AI methods relying mostly on using effective game tree search algorithms, carefully tuned hand-crafted evaluation functions or hardware-based brute-force methods. On the other hand, it should be noted that the aim of this book is by no means to underestimate the achievements of traditional AI methods in game playing domain. On the contrary, the accomplishments of AI approaches are undisputable and speak for themselves. The goal is rather to express my belief that other alternative ways of developing mind game playing machines are possible and urgently needed.