Advances in Computational Intelligence
IEEE World Congress on Computational Intelligence, WCCI 2012, Brisbane, Australia, June 10-15, 2012. Plenary/Invited Lectures
Published on 6. July 2012
VIII, 284 pages
978-3-642-30687-7 (ISBN)
Description
This state-of-the-art survey offers a renewed and refreshing focus on the progress in evolutionary computation, in neural networks, and in fuzzy systems. The book presents the expertise and experiences of leading researchers spanning a diverse spectrum of computational intelligence in these areas. The result is a balanced contribution to the research area of computational intelligence that should serve the community not only as a survey and a reference, but also as an inspiration for the future advancement of the state of the art of the field. The 13 selected chapters originate from lectures and presentations given at the IEEE World Congress on Computational Intelligence, WCCI 2012, held in Brisbane, Australia, in June 2012.
More details
Other editions
Additional editions
Jing Liu | Cesare Alippi | Bernadette Bouchon-Meunier
Advances in Computational Intelligence
IEEE World Congress on Computational Intelligence, WCCI 2012, Brisbane, Australia, June 10-15, 2012. Plenary/Invited Lectures
Book
05/2012
1st Edition
Springer
€53.49
Shipment within 7-9 days
Content
- Title
- Preface
- Table of Contents
- Lazy Meta-Learning: Creating Customized Model Ensembles on Demand
- Analytic Model Building in the Near Future
- Multiple Sources of Analytic Models Enabled by Cloud Computing
- Prognostics and Health Management (PHM) Motivation for Analytics
- The Novel Idea
- Paper Organization
- Related Work
- Model Ensembles
- Meta- Learning and Lazy Learning
- MCDM: Selection of Best Model Ensemble Based on Constrained Multi-Criteria
- Summary of the Approach
- Cloud Computing, the Enabler
- Lazy Meta-Learning
- MCDM Process for Model Creation and Dynamic Model Assembly
- (The Devil Is in the) Details of Our Approach
- Model Creation
- Dynamic Model Assembly on Demand
- Dynamic Model Fusion
- Customized Analytics Applied to Power Plant Management
- Problem Definition
- Preliminary Experimental Results
- Conclusions
- Analysis for Regression Problems
- Future work for Classification Problems
- References
- Multiagent Learning through Neuroevolution
- Introduction
- Setting up Multiagent Neuroevolution
- Predator-Prey Environment
- The Multi-component ESP Neuroevolution Method
- Experimental Setting Results
- Experimental Setting Conclusions
- Combining Evolution with Social Learning
- Motivation for Social Learning
- The Foraging Domain
- The NEAT Neuroevolution Method
- Social Learning Results
- Social Learning Conclusions
- Evaluating Multiagent Performance
- Motivation
- The NERO Domain
- Evaluation Results
- Evaluation Conclusions
- Discussion and Future Work
- Conclusion
- References
- Reverse-Engineering the Human Auditory Pathway
- Neuroscience Advances in 2003-2010 Illuminate Cortical Architecture
- Compute Capacity in 2012 Is Capable of Comprehensive Simulation and Visualization of the Multi-representation System
- Next Steps in Neuroscience Research for the Next Decade 2010-2020
- Non-technical Issues: Collaboration and Funding for 2010-2020
- Conclusions
- References
- Unpacking and Understanding Evolutionary Algorithms
- Introduction
- Evolutionary Optimisation
- Evolutionary Learning
- Evolutionary Design
- Theoretical Foundations of Evolutionary Computation
- Evolutionary Algorithms and Drift Analysis
- Modelling EAs Using Stochastic Processes
- Conditions for Polynomial Average Computation Times
- Conditions for Exponential Average Computation Time
- Problem Classification: EA-hard vs EA-easy
- Is a Large Population Always Helpful?
- Impact of Crossover
- Interaction between Operators/Parameters
- Estimation of Distribution Algorithms (EDAs)
- Concluding Remarks
- References
- Representation in Evolutionary Computation
- Representation in Self-avoiding Walks
- Representation in Game-Playing Agents
- Results
- Representation in Real Optimization
- Representations
- Comparing the Direct and Sierpinski Representations
- Comparison of the Direct and Gene Expression Representations
- Representation in Automatic Content Generations
- Results
- Discussion and Conclusions
- References
- Quo Vadis, Evolutionary Computation?
- Inspiration
- What Is an Evolutionary Algorithm?
- What Is 'Practice'? What Is a Real-World Application?
- Theory versus Practice
- Conclusions and Recommendations
- What Are the Practical Contributions Coming from the Theory of Evolutionary Algorithms?
- How Do Evolutionary Algorithms Compare with Operation Research Methods in Real-World Applications?
- Why Do So Few Papers on Evolutionary Algorithms Describe Real-World Applications?
- For What Type of Problems Evolutionary Algorithm Is "The Best" Method?
- References
- Probabilistic Graphical Approaches for Learning, Modeling, and Sampling in Evolutionary Multi-objective Optimization
- Introduction
- Probabilistic Graphical Models in Multi-objective Evolutionary Algorithms
- Restricted Boltzmann Machine (RBM)
- Training
- Modeling
- Sampling
- Learning Capability of REDA
- How and What Information Is Captured in an RBM.
- How to Effectively Train an RBM in the Evolutionary Perspective.
- What Can Be Elucidated from the Energy Values of an RBM in the Fitness Landscape Perspective.
- Algorithmic Process Flow
- Restricted Boltzmann Machine-Based Estimation of Distribution Algorithm for Solving Multi-objective Optimization Problems
- REDA with Clustering for Solving High Dimensional Problems
- An Energy-Based Sampling Mechanism of REDA
- REDA in Noisy Environments
- REDA for Solving the Multi-objective Multiple Traveling Salesman Problem
- Problem Formulation.
- Hybrid Adaptive MOEAs for Solving Continuous MOPs
- Conclusion
- References
- The Quest for Transitivity, a Showcase of Fuzzy Relational Calculus
- Introduction
- Relational Frameworks and Their Transitivity
- Fuzzy Relations
- Reciprocal Relations
- Stochastic Transitivity.
- FG-Transitivity.
- Cycle-Transitivity.
- A Frequentist Interpretation.
- Similarity of Fuzzy Sets
- Basic Notions
- A Logical Approach
- A Cardinal Approach
- Classical Cardinality-Based Similarity Measures.
- Fuzzy Cardinality-Based Similarity Measures.
- Bell-Inequalities and Preservation of Transitivity.
- Comparison of Random Variables
- Dice-Transitivity
- A Method for Comparing Random Variables
- Artificial Coupling of Random Variables
- Comparison of Special Independent Random Variables
- Mutual Rank Transitivity in Posets
- Conclusion
- References
- Cognition-Inspired Fuzzy Modelling
- Introduction
- Similarity Judgments
- Geometric Approach: Metric Properties
- Cognitive Approach: Experimental Critics
- Feature-Based Approach: Cognitive Properties
- Comparison of Measures of Similarity
- Families of Measures of Similarity
- Value-Based Comparison
- Order-Based Comparison
- Prototype-Based Categorization
- Basic Principles
- Typicality, Graduality, Conceptual Combination and Fuzzy Logic
- Osherson and Smith's Critics
- Answers to Osherson and Smith's Critics
- Fuzzy Prototypes Construction and Categorisation
- Basic Principles of Construction
- Fuzzy Prototypes and Conceptual Combination
- Fuzzy Prototypes for Classification
- Extended Principle
- Conclusion
- References
- A Unified Fuzzy Model-Based Framework for Modeling and Control of Complex Systems: From Flying Vehicle Control to Brain-Machine Cooperative Control
- Introduction
- Micro Helicopter Dynamics
- Polynomial Fuzzy Model and SOS-Based Designs
- Polynomial Fuzzy Model and Controller
- Stable Control
- Guaranteed Cost Control
- Controller Designs
- LMI Design Approach
- Simulation Results
- Vision-Based Micro Helicopter Control in Real Environments
- Experimental System
- Controller Design
- Experimental Results
- Conclusions
- References
- Predictive Learning, Knowledge Discovery and Philosophy of Science
- Introduction
- Classical Philosophy of Science
- Predictive Learning and Knowledge Discovery
- Practical Aspects of Predictive Data-Analytic Modeling
- Summary and Conclusions
- References
- Evolving Spiking Neural Networks and Neurogenetic Systems for Spatio- and Spectro-Temporal Data Modelling and Pattern Recognition
- Spatio- and Spectro-Temporal Data Modelling and Pattern Recognition
- Single Spiking Neuron Models
- A Biological Neuron
- Single Neuron Models
- A Neurogenetic Model of a Neuron
- Learning and Memory in a Spiking Neuron
- General Classification
- The STDP Learning Rule
- Spike Driven Synaptic Plasticity (SDSP)
- Rank-Order Learning
- Combined Rank-Order and Temporal Learning
- STPR in a Single Neuron
- Evolving Spiking Neural Networks
- Computational Neurogenetic Models (CNGM)
- SNN Software and Hardware Implementations to Support STPR
- Current and Future Applications of eSNN and CNGM for STPR
- References
- Uncovering the Neural Code Using a Rat Model during a Learning Control Task
- Introduction
- Single Unit Recording from Behaving Rats
- Animal Handling and Training Procedures
- Surgical Procedures
- Electrophysiology
- Behavioral Task
- Spike Detection Based on Wavelet Transform
- Introduction to Spike Detection
- Working Principle of the Multiscale Correlation of Wavelet Coefficients (MCWC)
- Detection Performance Evaluation
- Cortical Neural Modifications during a Cognitive Learning Control Task
- Characterizing Cortical Neural Modifications Using Firing Rates
- Role of Motor Cortical Neurons in a Directional and Sequential Control Task
- Conclusion
- References
- Author Index
