Computational Intelligence A Methodological Introduction

Computational intelligence (CI) encompasses a range of nature-inspired methods that exhibit intelligent behavior in complex environments.

This clearly-structured, classroom-tested textbook/reference presents a methodical introduction to the field of CI. Providing an authoritative insight into all that is necessary for the successful application of CI methods, the book describes fundamental concepts and their practical implementations, and explains the theoretical background underpinning proposed solutions to common problems. Only a basic knowledge of mathematics is required.

Topics and features: provides electronic supplementary material at an associated website, including module descriptions, lecture slides, exercises with solutions, and software tools; contains numerous examples and definitions throughout the text; presents self-contained discussions on artificial neural networks, evolutionary algorithms, fuzzy systems and Bayesian networks; covers the latest approaches, including ant colony optimization and probabilistic graphical models; written by a team of highly-regarded experts in CI, with extensive experience in both academia and industry.

Students of computer science will find the text a must-read reference for courses on artificial intelligence and intelligent systems. The book is also an ideal self-study resource for researchers and practitioners involved in all areas of CI.

Introduction

Part I: Neural Networks

Introduction

Threshold Logic Units

General Neural Networks

Multi-Layer Perceptrons

Radial Basis Function Networks

Self-Organizing Maps

Hopfield Networks

Recurrent Networks

Mathematical Remarks

Part II: Evolutionary Algorithms

Introduction to Evolutionary Algorithms

Elements of Evolutionary Algorithms

Fundamental Evolutionary Algorithms

Special Applications and Techniques

Part III: Fuzzy Systems

Fuzzy Sets and Fuzzy Logic

The Extension Principle

Fuzzy Relations

Similarity Relations

Fuzzy Control

Fuzzy Clustering

Part IV: Bayes Networks

Introduction to Bayes Networks

Elements of Probability and Graph Theory

Decompositions

Evidence Propagation

Learning Graphical Models

Rudolf Kruse is a full professor at the Department of Computer Science of the Otto-von-Guericke University of Magdeburg, Germany, where he leads the working group on computational intelligence. Christian Moewes and Pascal Held are research assistants at the same institution. Christian Borgelt is a principal researcher at the European Centre for Soft Computing, Mieres, Spain. Frank Klawonn is a Professor at the Department of Computer Science of Ostfalia University of Applied Sciences, Wolfenbüttel, Germany. Matthias Steinbrecher is a member of the SAP Innovation Center, Potsdam, Germany.