CHF180.90
Download steht sofort bereit
This two volume set LNCS 5163 and LNCS 5164 constitutes the refereed proceedings of the 18th International Conference on Artificial Neural Networks, ICANN 2008, held in Prague Czech Republic, in September 2008.
The 200 revised full papers presented were carefully reviewed and selected from more than 300 submissions. The first volume contains papers on mathematical theory of neurocomputing, learning algorithms, kernel methods, statistical learning and ensemble techniques, support vector machines, reinforcement learning, evolutionary computing, hybrid systems, self-organization, control and robotics, signal and time series processing and image processing.
Inhalt
Mathematical Theory of Neurocomputing.- Dimension Reduction for Mixtures of Exponential Families.- Several Enhancements to Hermite-Based Approximation of One-Variable Functions.- Multi-category Bayesian Decision by Neural Networks.- Estimates of Network Complexity and Integral Representations.- Reliability of Cross-Validation for SVMs in High-Dimensional, Low Sample Size Scenarios.- Generalization of Concave and Convex Decomposition in Kikuchi Free Energy.- Analysis of Chaotic Dynamics Using Measures of the Complex Network Theory.- Global Dynamics of Finite Cellular Automata.- Learning Algorithms.- Semi-supervised Learning of Tree-Structured RBF Networks Using Co-training.- A New Type of ART2 Architecture and Application to Color Image Segmentation.- BICA: A Boolean Indepenedent Component Analysis Approach.- Improving the Learning Speed in 2-Layered LSTM Network by Estimating the Configuration of Hidden Units and Optimizing Weights Initialization.- Manifold Construction Using the Multilayer Perceptron.- Improving Performance of a Binary Classifier by Training Set Selection.- An Overcomplete ICA Algorithm by InfoMax and InfoMin.- OP-ELM: Theory, Experiments and a Toolbox.- Robust Nonparametric Probability Density Estimation by Soft Clustering.- Natural Conjugate Gradient on Complex Flag Manifolds for Complex Independent Subspace Analysis.- Quadratically Constrained Quadratic Programming for Subspace Selection in Kernel Regression Estimation.- The Influence of the Risk Functional in Data Classification with MLPs.- Nonnegative Least Squares Learning for the Random Neural Network.- Kernel Methods, Statistical Learning, and Ensemble Techniques.- Sparse Bayes Machines for Binary Classification.- Tikhonov Regularization Parameter in Reproducing Kernel Hilbert Spaces with Respect to the Sensitivity of the Solution.- Mixture of Expert Used to Learn Game Play.- Unsupervised Bayesian Network Learning for Object Recognition in Image Sequences.- Using Feature Distribution Methods in Ensemble Systems Combined by Fusion and Selection-Based Methods.- Bayesian Ying-Yang Learning on Orthogonal Binary Factor Analysis.- A Comparative Study on Data Smoothing Regularization for Local Factor Analysis.- Adding Diversity in Ensembles of Neural Networks by Reordering the Training Set.- New Results on Combination Methods for Boosting Ensembles.- Support Vector Machines.- Batch Support Vector Training Based on Exact Incremental Training.- A Kernel Method for the Optimization of the Margin Distribution.- A 4-Vector MDM Algorithm for Support Vector Training.- Implementation Issues of an Incremental and Decremental SVM.- Online Clustering of Non-stationary Data Using Incremental and Decremental SVM.- Support Vector Machines for Visualization and Dimensionality Reduction.- Reinforcement Learning.- Multigrid Reinforcement Learning with Reward Shaping.- Self-organized Reinforcement Learning Based on Policy Gradient in Nonstationary Environments.- Robust Population Coding in Free-Energy-Based Reinforcement Learning.- Policy Gradients with Parameter-Based Exploration for Control.- A Continuous Internal-State Controller for Partially Observable Markov Decision Processes.- Episodic Reinforcement Learning by Logistic Reward-Weighted Regression.- Error-Entropy Minimization for Dynamical Systems Modeling.- Evolutionary Computing.- Hybrid Evolution of Heterogeneous Neural Networks.- Ant Colony Optimization with Castes.- Neural Network Ensembles for Classification Problems Using Multiobjective Genetic Algorithms.- Analysis of Vestibular-Ocular Reflex by Evolutionary Framework.- Fetal Weight Prediction Models: Standard Techniques or Computational Intelligence Methods?.- Evolutionary Canonical Particle Swarm Optimizer - A Proposal of Meta-optimization in Model Selection.- Hybrid Systems.- Building Localized Basis Function Networks Using Context Dependent Clustering.- Adaptation of Connectionist Weighted Fuzzy Logic Programs with Kripke-Kleene Semantics.- Neuro-fuzzy System for Road Signs Recognition.- Neuro-inspired Speech Recognition with Recurrent Spiking Neurons.- Predicting the Performance of Learning Algorithms Using Support Vector Machines as Meta-regressors.- Municipal Creditworthiness Modelling by Kohonen's Self-Organizing Feature Maps and Fuzzy Logic Neural Networks.- Implementing Boolean Matrix Factorization.- Application of Potts-Model Perceptron for Binary Patterns Identification.- Using ARTMAP-Based Ensemble Systems Designed by Three Variants of Boosting.- Self-organization.- Matrix Learning for Topographic Neural Maps.- Clustering Quality and Topology Preservation in Fast Learning SOMs.- Enhancing Topology Preservation during Neural Field Development Via Wiring Length Minimization.- Adaptive Translation: Finding Interlingual Mappings Using Self-Organizing Maps.- Self-Organizing Neural Grove: Efficient Multiple Classifier System with Pruned Self-Generating Neural Trees.- Self-organized Complex Neural Networks through Nonlinear Temporally Asymmetric Hebbian Plasticity.- Temporal Hebbian Self-Organizing Map for Sequences.- FLSOM with Different Rates for Classification in Imbalanced Datasets.- A Self-organizing Neural System for Background and Foreground Modeling.- Analyzing the Behavior of the SOM through Wavelet Decomposition of Time Series Generated during Its Execution.- Decreasing Neighborhood Revisited in Self-Organizing Maps.- A New GHSOM Model Applied to Network Security.- Reduction of Visual Information in Neural Network Learning Visualization.- Control and Robotics.- Heuristiscs-Based High-Level Strategy for Multi-agent Systems.- Echo State Networks for Online Prediction of Movement Data - Comparing Investigations.- Comparison of RBF Network Learning and Reinforcement Learning on the Maze Exploration Problem.- Modular Neural Networks for Model-Free Behavioral Learning.- From Exploration to Planning.- Signal and Time Series Processing.- Sentence-Level Evaluation Using Co-occurences of N-Grams.- Identifying Single Source Data for Mixing Matrix Estimation in Instantaneous Blind Source Separation.- ECG Signal Classification Using GAME Neural Network and Its Comparison to Other Classifiers.- Predictive Modeling with Echo State Networks.- Sparse Coding Neural Gas for the Separation of Noisy Overcomplete Sources.- Mutual Information Based Input Variable Selection Algorithm and Wavelet Neural Network for Time Series Prediction.- Stable Output Feedback in Reservoir Computing Using Ridge Regression.- Image Processing.- Spatio-temporal Summarizing Method of Periodic Image Sequences with Kohonen Maps.- Image Classification by Histogram Features Created with Learning Vector Quantization.- A Statistical Model for Histogram Refinement.- Efficient Video Shot Summarization Using an Enhanced Spectral Clustering Approach.- Surface Reconstruction Techniques Using Neural Networks to Recover Noisy 3D Scenes.- A Spatio-temporal Extension of the SUSAN-Filter.- A Neighborhood-Based Competitive Network for Video Segmentation and Object Detection.- A Hierarchic Method for Footprint Segmentation Based on SOM.- Co-occurrence Matrixes for the Quality Assessment of Coded Images.- Semantic Adaptation of Neural Network Classifiers in Image Segmentation.- Partially Monotone Networks Applied to Breast Cancer Detection on Mammogram…