Full Description
Recent years have seen numerous applications across a variety of fields using various techniques of Computational Intelligence. This book, one of a series on the foundations of Computational Intelligence, is focused on learning and approximation.
Contents
Part I Function Approximation.- Machine Learning and Genetic Regulatory Networks: A Review and a Roadmap.- Automatic Approximation of Expensive Functions with Active Learning.- New Multi-Objective Algorithms for Neural Network Training applied to Genomic Classification Data.- An Evolutionary Approximation for the Coefficients of Decision Functions within a Support Vector Machine Learning Strategy.- Part II Connectionist Learning.- Meta-learning and Neurocomputing - A New Perspective for Computational Intelligence.- Three-term Fuzzy Back-propagation.- Entropy Guided Transformation Learning.- Artificial Development.- Robust Training of Artificial Feed-forward Neural Networks.- Workload Assignment In Production Networks By Multi-Agent Architecture.- Part III Knowledge Representation and Acquisition.- Extensions to Knowledge Acquisition and Effect of Multimodal Representation in Unsupervised Learning.- A New Implementation for Neural Networks in Fourier-Space.- Part IV Learning and Visualization.- Dissimilarity Analysis and Application to Visual Comparisons.- Dynamic Self-Organising Maps: Theory, Methods and Applications.- Hybrid Learning Enhancement of RBF Network with Particle Swarm Optimization.
