Oppositional Concepts in Computational Intelligence

Opposition permeates nature, but because of a lack of accepted mathematical formalism, the field is rarely studied outside of philosophy and logic. This book is the first ever to elucidate and explore opposition-based computing and concepts.

Theoppositeofacorrectstatementisafalsestatement.Buttheopposite of a profound truth may well be another profound truth. Niels Bohr This volume is motivated in part by the observation that opposites permeate everything around us, in some form or another. Its study has attracted the attention of countless minds for at least 2500 years. However, due to the lack of an accepted mathematical formalism for opposition it has not been explicitly studiedtoanygreatlengthin?eldsoutsideofphilosophyandlogic.This,despite the fact that we observe opposition everywhere in nature, our minds seem to divide the world into entities and opposite entities; indeed we use opposition everyday. We have become so accustomed to opposition that its existence is accepted, not usually questioned and its importance is constantly overlooked. On one hand, this volume is a ?st attempt to bring together researchers who are inquiring into the complementary nature of systems and processes and, on the other hand, provide some elementary components for a framework to establish a formalism for opposition-based computing. From a computational intelligence perspective, many successful opposition-based concepts have been in existence for a long time. It is not our intention to recast these existing methods, rather to elucidate that, while diverse, they all share the commonality of opposition - in one form or another, either implicitly or explicitly. To this end, we have attempted to provide rough guidelines to understand what makes concepts oppositional.

Describes and presents opposition-based computing and concepts

Klappentext

This volume is motivated in part by the observation that opposites permeate everything around us, in some form or another. Its study has attracted the attention of countless minds for at least 2500 years. However, due to the lack of an accepted mathematical formalism for opposition it has not been explicitly studied to any great length in fields outside of philosophy and logic. Despite the fact that we observe opposition everywhere in nature, our minds seem to divide the world into entities and opposite entities; indeed we use opposition everyday. We have become so accustomed to opposition that its existence is accepted, not usually questioned and its importance is constantly overlooked.

On the one hand, this volume is a fist attempt to bring together researchers who are inquiring into the complementary nature of systems and processes and, on the other hand, it provides some elementary components for a framework to establish a formalism for opposition-based computing. From a computational intelligence perspective, many successful opposition-based concepts have been in existence for a long time. It is not the authors intention to recast these existing methods, rather to elucidate that, while diverse, they all share the commonality of opposition - in one form or another, either implicitly or explicitly. Therefore they have attempted to provide rough guidelines to understand what makes concepts "oppositional".

Inhalt
I: Motivations and Theory.- Opposition-Based Computing.- Antithetic and Negatively Associated Random Variables and Function Maximization.- Opposition and Circularity.- II: Search and Reasoning.- Collaborative vs. Conflicting Learning, Evolution and Argumentation.- Proof-Number Search and Its Variants.- III: Optimization.- Improving the Exploration Ability of Ant-Based Algorithms.- Differential Evolution Via Exploiting Opposite Populations.- Evolving Opposition-Based Pareto Solutions: Multiobjective Optimization Using Competitive Coevolution.- IV: Learning.- Bayesian Ying-Yang Harmony Learning for Local Factor Analysis: A Comparative Investigation.- The Concept of Opposition and Its Use in Q-Learning and Q(?) Techniques.- Two Frameworks for Improving Gradient-Based Learning Algorithms.- V: Real World Applications.- Opposite Actions in Reinforced Image Segmentation.- Opposition Mining in Reservoir Management.