Artificial Neural Networks -- Icann 2002: International Conference, Madrid, Spain, August 28-30, 2002. Proceedings

ISBN-13: 9783540440741 / Angielski / Miękka / 2002 / 1384 str.

J. R. Dorronsoro; Jose R. Dorronsoro;Springer-Verlag

Opis

The International Conferences on Arti?cial Neural Networks, ICANN, have been held annually since 1991 and over the years have become the major European meeting in neural networks. This proceedings volume contains all the papers presented at ICANN 2002, the 12th ICANN conference, held in August 28 30, 2002 at the Escuela Tecnica Superior de Informatica of the Universidad Autonoma de Madrid and organized by its Neural Networks group. ICANN 2002 received a very high number of contributions, more than 450. Almost all papers were revised by three independent reviewers, selected among the more than 240 serving at this year s ICANN, and 221 papers were ?nally selected for publication in these proceedings (due to space considerations, quite a few good contributions had to be left out). I would like to thank the Program Committee and all the reviewers for the great collective e?ort and for helping us to have a high quality conference."

Spis treści

Computational Neuroscience.- A Neurodynamical Theory of Visual Attention: Comparisons with fMRI- and Single-Neuron Data.- A Neural Model of Spatio Temporal Coordination in Prehension.- Stabilized Dynamics in Physiological and Neural Systems Despite Strongly Delayed Feedback.- Learning Multiple Feature Representations from Natural Image Sequences.- Analysis of Biologically Inspired Small-World Networks.- Receptive Fields Similar to Simple Cells Maximize Temporal Coherence in Natural Video.- Noise Induces Spontaneous Synchronous Aperiodic Activity in EI Neural Networks.- Multiple Forms of Activity-Dependent Plasticity Enhance Information Transfer at a Dynamic Synapse.- Storage Capacity of Kernel Associative Memories.- Macrocolumns as Decision Units.- Nonlinear Analysis of Simple Cell Tuning in Visual Cortex.- Clustering within Integrate-and-Fire Neurons for Image Segmentation.- Symmetry Detection Using Global-Locally Coupled Maps.- Applying Slow Feature Analysis to Image Sequences Yields a Rich Repertoire of Complex Cell Properties.- Combining Multimodal Sensory Input for Spatial Learning.- A Neural Network Model Generating Invariance for Visual Distance.- Modeling Neural Control of Locomotion: Integration of Reflex Circuits with CPG.- Comparing the Information Encoded by Different Brain Areas with Functional Imaging Techniques.- Mean-Field Population Dynamics of Spiking Neurons with Random Synaptic Delays.- Stochastic Resonance and Finite Resolution in a Network of Leaky Integrate-and-Fire Neurons.- Reducing Communication for Distributed Learning in Neural Networks.- Flow Diagrams of the Quadratic Neural Network.- Dynamics of a Plastic Cortical Network.- Non-monotonic Current-to-Rate Response Function in a Novel Integrate-and-Fire Model Neuron.- Small-World Effects in Lattice Stochastic Diffusion Search.- A Direction Sensitive Network Based on a Biophysical Neurone Model.- Characterization of Triphasic Rhythms in Central Pattern Generators (I): Interspike Interval Analysis.- Characterization of Triphasic Rhythms in Central Pattern Generators (II): Burst Information Analysis.- Neural Coding Analysis in Retinal Ganglion Cells Using Information Theory.- Firing Rate Adaptation without Losing Sensitivity to Input Fluctuations.- Does Morphology Influence Temporal Plasticity?.- Attractor Neural Networks with Hypercolumns.- Edge Detection and Motion Discrimination in the Cuneate Nucleus.- Encoding the Temporal Statistics of Markovian Sequences of Stimuli in Recurrent Neuronal Networks.- Multi-stream Exploratory Projection Pursuit for the Formation of Complex Cells Similar to Visual Cortical Neurons.- A Corticospinal Network for Control of Voluntary Movements of a Physiologically Based Experimental Platform.- Firing Rate for a Generic Integrate-and-Fire Neuron with Exponentially Correlated Input.- Iterative Population Decoding Based on Prior Beliefs.- When NMDA Receptor Conductances Increase Inter- spike Interval Variability.- Spike- Driven Synaptic Plasticity for Learning Correlated Patterns of Asynchronous Activity.- A Model of Human Cortical Microcircuits for the Study of the Development of Epilepsy.- On the Computational Power of Neural Microcircuit Models: Pointers to the Literature.- Connectionist Cognitive Science.- Networking with Cognitive Packets.- Episodic Memory: A Connectionist Interpretation.- Action Scheme Scheduling with a Neural Architecture: A Prefrontal Cortex Approach.- Associative Arithmetic with Boltzmann Machines: The Role of Number Representations.- Learning the Long-Term Structure of the Blues.- Recursive Neural Networks Applied to Discourse Representation Theory.- Recurrent Neural Learning for Helpdesk Call Routing.- An Approach to Encode Multilayer Perceptrons.- Dynamic Knowledge Representation in Connectionist Systems.- Generative Capacities of Cellular Automata Codification for Evolution of NN Codification.- Data Analysis and Pattern Recognition.- Entropic Measures with Radial Basis Units.- New Methods for Splice Site Recognition.- A Weak Condition on Linear Independence of Unscaled Shifts of a Function and Finite Mappings by Neural Networks.- Identification of Wiener Model Using Radial Basis Functions Neural Networks.- A New Learning Algorithm for Mean Field Boltzmann Machines.- A Continuous Restricted Boltzmann Machine with a Hardware- Amenable Learning Algorithm.- Human Recognition by Gait Analysis Using Neural Networks.- Learning Vector Quantization for Multimodal Data.- Learning the Dynamic Neural Networks with the Improvement of Generalization Capabilities.- Model Clustering for Neural Network Ensembles.- Does Crossover Probability Depend on Fitness and Hamming Differences in Genetic Algorithms?.- Extraction of Fuzzy Rules Using Sensibility Analysis in a Neural Network.- A Simulated Annealing and Resampling Method for Training Perceptrons to Classify Gene-Expression Data.- Neural Minimax Classifiers.- Sampling Parameters to Estimate a Mixture Distribution with Unknown Size.- Selecting Neural Networks for Making a Committee Decision.- High-Accuracy Mixed-Signal VLSI for Weight Modification in Contrastive Divergence Learning.- Data Driven Generation of Interactions for Feature Binding and Relaxation Labeling.- A Hybrid Two-Stage Fuzzy ARTMAP and LVQ Neuro-fuzzy System for Online Handwriting Recognition.- A New Learning Method for Piecewise Linear Regression.- Stable Adaptive Momentum for Rapid Online Learning in Nonlinear Systems.- Potential Energy and Particle Interaction Approach for Learning in Adaptive Systems.- Piecewise-Linear Approximation of Any Smooth Output Function on the Cellular Neural Network.- MDL Based Model Selection for Relevance Vector Regression.- On the Training of a Kolmogorov Network.- A New Method of Feature Extraction and Its Stability.- Visualization and Analysis of Web Navigation Data.- Missing Value Estimation Using Mixture of PCAs.- High Precision Measurement of Fuel Density Profiles in Nuclear Fusion Plasmas.- Heterogeneous Forests of Decision Trees.- Independent Component Analysis for Domain Independent Watermarking.- Applying Machine Learning to Solve an Estimation Problem in Software Inspections.- Clustering of Gene Expression Data by Mixture of PCA Models.- Selecting Ridge Parameters in Infinite Dimensional Hypothesis Spaces.- A New Sequential Algorithm for Regression Problems by Using Mixture Distribution.- Neural-Based Classification of Blocks from Documents.- Feature Selection via Genetic Optimization.- Neural Networks, Clustering Techniques, and Function Approximation Problems.- Evolutionary Training of Neuro-fuzzy Patches for Function Approximation.- Using Recurrent Neural Networks for Automatic Chromosome Classification.- A Mixed Ensemble Approach for the Semi-supervised Problem.- Using Perceptrons for Supervised Classification of DNA Microarray Samples: Obtaining the Optimal Level of Information and Finding Differentially Expressed Genes.- Lower Bounds for Training and Leave-One-Out Estimates of the Generalization Error.- SSA, SVD, QR-cp, and RBF Model Reduction.- Linkage Analysis: A Bayesian Approach.- On Linear Separability of Sequences and Structures.- Stability-Based Model Order Selection in Clustering with Applications to Gene Expression Data.- EM-Based Radial Basis Function Training with Partial Information.- Stochastic Supervised Learning Algorithms with Local and Adaptive Learning Rate for Recognising Hand-Written Characters.- Input and Output Feature Selection.- Optimal Extraction of Hidden Causes.- Towards a New Information Processing Measure for Neural Computation.- A Scalable and Efficient Probabilistic Information Retrieval and Text Mining System.- Maximum and Minimum Likelihood Hebbian Learning for Exploratory Projection Pursuit.- Learning Context Sensitive Languages with LSTM Trained with Kalman Filters.- Hierarchical Model Selection for NGnet Based on Variational Bayes Inference.- Multi-layer Perceptrons for Functional Data Analysis: A Projection Based Approach.- Natural Gradient and Multiclass NLDA Networks.- Kernel Methods.- A Greedy Training Algorithm for Sparse Least-Squares Support Vector Machines.- Selection of Meta-parameters for Support Vector Regression.- Kernel Matrix Completion by Semidefinite Programming.- Incremental Sparse Kernel Machine.- Frame Kernels for Learning.- Robust Cross-Validation Score Function for Non-linear Function Estimation.- Compactly Supported RBF Kernels for Sparsifying the Gram Matrix in LS-SVM Regression Models.- The Leave-One-Out Kernel.- Support Vector Representation of Multi-categorical Data.- Robust De-noising by Kernel PCA.- Maximum Contrast Classifiers.- Puncturing Multi-class Support Vector Machines.- Multi-dimensional Function Approximation and Regression Estimation.- Detecting the Number of Clusters Using a Support Vector Machine Approach.- Mixtures of Probabilistic PCAs and Fisher Kernels for Word and Document Modeling.- Robotics and Control.- Reinforcement Learning for Biped Locomotion.- Dynamical Neural Schmitt Trigger for Robot Control.- Evolutionary Artificial Neural Networks for Quadruped Locomotion.- Saliency Maps Operating on Stereo Images Detect Landmarks and Their Distance.- A Novel Approach to Modelling and Exploiting Uncertainty in Stochastic Control Systems.- Tool Wear Prediction in Milling Using Neural Networks.- Speeding-up Reinforcement Learning with Multi-step Actions.- Extended Kalman Filter Trained Recurrent Radial Basis Function Network in Nonlinear System Identification.- Integration of Metric Place Relations in a Landmark Graph.- Hierarchical Object Classification for Autonomous Mobile Robots.- Self Pruning Gaussian Synapse Networks for Behavior Based Robots.- Second-Order Conditioning in Mobile Robots.- An Optimal Sensor Morphology Improves Adaptability of Neural Network Controllers.- Learning Inverse Kinematics via Cross-Point Function Decomposition.- Selforganization.- The Principal Components Analysis Self-Organizing Map.- Using Smoothed Data Histograms for Cluster Visualization in Self-Organizing Maps.- Rule Extraction from Self-Organizing Networks.- Predictive Self-Organizing Map for Vector Quantization of Migratory Signals.- Categorical Topological Map.- Spike-Timing Dependent Competitive Learning of Integrate-and-Fire Neurons with Active Dendrites.- Parametrized SOMs for Object Recognition and Pose Estimation.- An Effective Traveling Salesman Problem Solver Based on Self-Organizing Map.- Coordinating Principal Component Analyzers.- Lateral Interactions in Self-Organizing Maps.- Complexity Selection of the Self-Organizing Map.- Nonlinear Projection with the Isotop Method.- Asymptotic Level Density of the Elastic Net Self-Organizing Feature Map.- Local Modeling Using Self-Organizing Maps and Single Layer Neural Networks.- Distance Matrix Based Clustering of the Self-Organizing Map.- Mapping the Growing Neural Gas to Situation Calculus.- Robust Unsupervised Competitive Neural Network by Local Competitive Signals.- Goal Sequencing for Construction Agents in a Simulated Environment.- Nonlinear Modeling of Dynamic Systems with the Self-Organizing Map.- Implementing Relevance Feedback as Convolutions of Local Neighborhoods on Self-Organizing Maps.- A Pareto Self-Organizing Map.- A SOM Variant Based on the Wilcoxon Test for Document Organization and Retrieval.- Learning More Accurate Metrics for Self-Organizing Maps.- Correlation Visualization of High Dimensional Data Using Topographic Maps.- Signal and Time Series Analysis.- Continuous Unsupervised Sleep Staging Based on a Single EEG Signal.- Financial APT-Based Gaussian TFA Learning for Adaptive Portfolio Management.- On Convergence of an Iterative Factor Estimate Algorithm for the NFA Model.- Error Functions for Prediction of Episodes of Poor Air Quality.- Adaptive Importance Sampling Technique for Neural Detector Training.- State Space Neural Networks for Freeway Travel Time Prediction.- Overcomplete ICA with a Geometric Algorithm.- Improving Long- Term Online Prediction with Decoupled Extended Kalman Filters.- Market Modeling Based on Cognitive Agents.- An Efficiently Focusing Large Vocabulary Language Model.- Neuro- classification of Bill Fatigue Levels Based on Acoustic Wavelet Components.- Robust Estimator for the Learning Process in Neural Networks Applied in Time Series.- An Improved Cumulant Based Method for Independent Component Analysis.- Finding the Optimal Continuous Model for Discrete Data by Neural Network Interpolation of Fractional Iteration.- Support Vector Robust Algorithms for Non- parametric Spectral Analysis.- Support Vector Method for ARMA System Identification: A Robust Cost Interpretation.- Dynamics of ICA for High- Dimensional Data.- Beyond Comon’s Identifiability Theorem for Independent Component Analysis.- Temporal Processing of Brain Activity for the Recognition of EEG Patterns.- Critical Assessment of Option Pricing Methods Using Artificial Neural Networks.- Single Trial Detection of EEG Error Potentials: A Tool for Increasing BCI Transmission Rates.- Dynamic Noise Annealing for Learning Temporal Sequences with Recurrent Neural Networks.- Convolutional Neural Networks for Radar Detection.- A Simple Generative Model for Single-Trial EEG Classification.- Robust Blind Source Separation Utilizing Second and Fourth Order Statistics.- Adaptive Differential Decorrelation: A Natural Gradient Algorithm.- An Application of SVM to Lost Packets Reconstruction in Voice-Enabled Services.- Baum-Welch Learning in Discrete Hidden Markov Models with Linear Factorial Constraints.- Mixtures of Autoregressive Models for Financial Risk Analysis.- Vision and Image Processing.- Kernel-Based 3D Object Representation.- Multiresolution Support for Adaptive Image Restoration Using Neural Networks.- Audio-Visual Speech Recognition One Pass Learning with Spiking Neurons.- An Algorithm for Image Representation as Independent Levels of Resolution.- Circular Back-Propagation Networks for Measuring Displayed Image Quality.- Unsupervised Learning of Combination Features for Hierarchical Recognition Models.- Type of Blur and Blur Parameters Identification Using Neural Network and Its Application to Image Restoration.- Using Neural Field Dynamics in the Context of Attentional Control.- A Component Association Architecture for Image Understanding.- Novelty Detection in Video Surveillance Using Hierarchical Neural Networks.- Vergence Control and Disparity Estimation with Energy Neurons: Theory and Implementation.- Population Coding of Multiple Edge Orientation.- A Neural Model of the Fly Visual System Applied to Navigational Tasks.- A Neural Network Model for Pattern Recognition Based on Hypothesis and Verification with Moving Region of Attention.- Automatic Fingerprint Verification Using Neural Networks.- Fusing Images with Multiple Focuses Using Support Vector Machines.- An Analog VLSI Pulsed Neural Network for Image Segmentation Using Adaptive Connection Weights.- Kohonen Maps Applied to Fast Image Vector Quantization.- Unsupervised - Neural Network Approach for Efficient Video Description.- Neural Networks Retraining for Unsupervised Video Object Segmentation of Videoconference Sequences.- Learning Face Localization Using Hierarchical Recurrent Networks.- A Comparison of Face Detection Algorithms.- Special Session: Adaptivity in Neural Computation.- Adaptive Model Selection for Digital Linear Classifiers.- Sequential Learning in Feedforward Networks: Proactive and Retroactive Interference Minimization.- Automatic Hyperparameter Tuning for Support Vector Machines.- Conjugate Directions for Stochastic Gradient Descent.- Special Session: Recurrent Neural Systems.- Architectural Bias in Recurrent Neural Networks — Fractal Analysis.- Continuous-State Hopfield Dynamics Based on Implicit Numerical Methods.- Time-Scaling in Recurrent Neural Learning.