Artificial Neural Networks - Icann 2009: 19th International Conference, Limassol, Cyprus, September 14-17, 2009, Proceedings, Part I

ISBN-13: 9783642042737 / Angielski / Miękka / 2009 / 1030 str.

Cesare Alippi

Opis

This volume is part of the two-volume proceedings of the 19th International Conf- ence on Artificial Neural Networks (ICANN 2009), which was held in Cyprus during September 14-17, 2009. The ICANN conference is an annual meeting sp- sored by the European Neural Network Society (ENNS), in cooperation with the - ternational Neural Network Society (INNS) and the Japanese Neural Network Society (JNNS). ICANN 2009 was technically sponsored by the IEEE Computational Intel- gence Society. This series of conferences has been held annually since 1991 in various European countries and covers the field of neurocomputing, learning systems and related areas. Artificial neural networks provide an information-processing structure inspired by biological nervous systems. They consist of a large number of highly interconnected processing elements, with the capability of learning by example. The field of artificial neural networks has evolved significantly in the last two decades, with active partici- tion from diverse fields, such as engineering, computer science, mathematics, artificial intelligence, system theory, biology, operations research, and neuroscience. Artificial neural networks have been widely applied for pattern recognition, control, optimization, image processing, classification, signal processing, etc.

Spis treści

Learning Algorithms.- Mutual Information Based Initialization of Forward-Backward Search for Feature Selection in Regression Problems.- Kernel Learning for Local Learning Based Clustering.- Projective Nonnegative Matrix Factorization with ?-Divergence.- Active Generation of Training Examples in Meta-Regression.- A Maximum-Likelihood Connectionist Model for Unsupervised Learning over Graphical Domains.- Local Feature Selection for the Relevance Vector Machine Using Adaptive Kernel Learning.- MINLIP: Efficient Learning of Transformation Models.- Efficient Uncertainty Propagation for Reinforcement Learning with Limited Data.- Optimal Training Sequences for Locally Recurrent Neural Networks.- Statistical Instance-Based Ensemble Pruning for Multi-class Problems.- Robustness of Kernel Based Regression: A Comparison of Iterative Weighting Schemes.- Mixing Different Search Biases in Evolutionary Learning Algorithms.- Semi-supervised Learning for Regression with Co-training by Committee.- An Analysis of Meta-learning Techniques for Ranking Clustering Algorithms Applied to Artificial Data.- Probability-Based Distance Function for Distance-Based Classifiers.- Constrained Learning Vector Quantization or Relaxed k-Separability.- Minimization of Quadratic Binary Functional with Additive Connection Matrix.- Mutual Learning with Many Linear Perceptrons: On-Line Learning Theory.- Computational Neuroscience.- Synchrony State Generation in Artificial Neural Networks with Stochastic Synapses.- Coexistence of Cell Assemblies and STDP.- Controlled and Automatic Processing in Animals and Machines with Application to Autonomous Vehicle Control.- Multiple Sound Source Localisation in Reverberant Environments Inspired by the Auditory Midbrain.- A Model of Neuronal Specialization Using Hebbian Policy-Gradient with “Slow” Noise.- How Bursts Shape the STDP Curve in the Presence/Absence of GABAergic Inhibition.- Optimizing Generic Neural Microcircuits through Reward Modulated STDP.- Calcium Responses Model in Striatum Dependent on Timed Input Sources.- Independent Component Analysis Aided Diagnosis of Cuban Spino Cerebellar Ataxia 2.- Hippocampus, Amygdala and Basal Ganglia Based Navigation Control.- A Framework for Simulation and Analysis of Dynamically Organized Distributed Neural Networks.- Continuous Attractors of Lotka-Volterra Recurrent Neural Networks.- Learning Complex Population-Coded Sequences.- Structural Analysis on STDP Neural Networks Using Complex Network Theory.- Time Coding of Input Strength Is Intrinsic to Synapses with Short Term Plasticity.- Information Processing and Timing Mechanisms in Vision.- Review of Neuron Types in the Retina: Information Models for Neuroengineering.- Brain Electric Microstate and Perception of Simultaneously Audiovisual Presentation.- A Model for Neuronal Signal Representation by Stimulus-Dependent Receptive Fields.- Hardware Implementations and Embedded Systems.- Area Chip Consumption by a Novel Digital CNN Architecture for Pattern Recognition.- Multifold Acceleration of Neural Network Computations Using GPU.- Training Recurrent Neural Network Using Multistream Extended Kalman Filter on Multicore Processor and Cuda Enabled Graphic Processor Unit.- A Non-subtraction Configuration of Self-similitude Architecture for Multiple-Resolution Edge-Filtering CMOS Image Sensor.- Current-Mode Computation with Noise in a Scalable and Programmable Probabilistic Neural VLSI System.- Minimising Contrastive Divergence with Dynamic Current Mirrors.- Spiking Neural Network Self-configuration for Temporal Pattern Recognition Analysis.- Image Recognition in Analog VLSI with On-Chip Learning.- Behavior Modeling by Neural Networks.- Statistical Parameter Identification of Analog Integrated Circuit Reverse Models.- A New FGMOST Euclidean Distance Computational Circuit Based on Algebraic Mean of the Input Potentials.- FPGA Implementation of Support Vector Machines for 3D Object Identification.- Reconfigurable MAC-Based Architecture for Parallel Hardware Implementation on FPGAs of Artificial Neural Networks Using Fractional Fixed Point Representation.- Self Organization.- A Two Stage Clustering Method Combining Self-Organizing Maps and Ant K-Means.- Image Theft Detection with Self-Organising Maps.- Improved Kohonen Feature Map Associative Memory with Area Representation for Sequential Analog Patterns.- Surface Reconstruction Method Based on a Growing Self-Organizing Map.- Micro-SOM: A Linear-Time Multivariate Microaggregation Algorithm Based on Self-Organizing Maps.- Identifying Clusters Using Growing Neural Gas: First Results.- Hierarchical Architecture with Modular Network SOM and Modular Reinforcement Learning.- Hybrid Systems for River Flood Forecasting Using MLP, SOM and Fuzzy Systems.- Topographic Mapping of Astronomical Light Curves via a Physically Inspired Probabilistic Model.- Generalized Self-Organizing Mixture Autoregressive Model for Modeling Financial Time Series.- Self-Organizing Map Simulations Confirm Similarity of Spatial Correlation Structure in Natural Images and Cortical Representations.- Intelligent Control and Adaptive Systems.- Height Defuzzification Method on L ??? Space.- An Additive Reinforcement Learning.- Neural Spike Suppression by Adaptive Control of an Unknown Steady State.- Combined Mechanisms of Internal Model Control and Impedance Control under Force Fields.- Neural Network Control of Unknown Nonlinear Systems with Efficient Transient Performance.- High-Order Fuzzy Switching Neural Networks: Application to the Tracking Control of a Class of Uncertain SISO Nonlinear Systems.- Neural and Hybrid Architectures.- A Guide for the Upper Bound on the Number of Continuous-Valued Hidden Nodes of a Feed-Forward Network.- Comparative Study of the CG and HBF ODEs Used in the Global Minimization of Nonconvex Functions.- On the Knowledge Organization in Concept Formation: An Exploratory Cognitive Modeling Study.- Dynamics of Incremental Learning by VSF-Network.- Kernel CMAC with Reduced Memory Complexity.- Model Complexity of Neural Networks and Integral Transforms.- Function Decomposition Network.- Improved Storage Capacity in Correlation Matrix Memories Storing Fixed Weight Codes.- Multiagent Reinforcement Learning with Spiking and Non-Spiking Agents in the Iterated Prisoner’s Dilemma.- Unsupervised Learning in Reservoir Computing: Modeling Hippocampal Place Cells for Small Mobile Robots.- Switching Hidden Markov Models for Learning of Motion Patterns in Videos.- Multimodal Belief Integration by HMM/SVM-Embedded Bayesian Network: Applications to Ambulating PC Operation by Body Motions and Brain Signals.- A Neural Network Model of Metaphor Generation with Dynamic Interaction.- Almost Random Projection Machine.- Optimized Learning Vector Quantization Classifier with an Adaptive Euclidean Distance.- Efficient Parametric Adjustment of Fuzzy Inference System Using Error Backpropagation Method.- Neuro-fuzzy Rough Classifier Ensemble.- Combining Feature Selection and Local Modelling in the KDD Cup 99 Dataset.- An Automatic Parameter Adjustment Method of Pulse Coupled Neural Network for Image Segmentation.- Pattern Identification by Committee of Potts Perceptrons.- Support Vector Machine.- Is Primal Better Than Dual.- A Fast BMU Search for Support Vector Machine.- European Option Pricing by Using the Support Vector Regression Approach.- Learning SVMs from Sloppily Labeled Data.- The GMM-SVM Supervector Approach for the Recognition of the Emotional Status from Speech.- A Simple Proof of the Convergence of the SMO Algorithm for Linearly Separable Problems.- Spanning SVM Tree for Personalized Transductive Learning.- Improving Text Classification Performance with Incremental Background Knowledge.- Empirical Study of the Universum SVM Learning for High-Dimensional Data.- Relevance Feedback for Content-Based Image Retrieval Using Support Vector Machines and Feature Selection.- Recurrent Neural Network.- Understanding the Principles of Recursive Neural Networks: A Generative Approach to Tackle Model Complexity.- An EM Based Training Algorithm for Recurrent Neural Networks.- Modeling D st  with Recurrent EM Neural Networks.- On the Quantification of Dynamics in Reservoir Computing.- Solving the CLM Problem by Discrete-Time Linear Threshold Recurrent Neural Networks.- Scalable Neural Networks for Board Games.- Reservoir Size, Spectral Radius and Connectivity in Static Classification Problems.

Blurb

This two volume set LNCS 5768 and LNCS 5769 constitutes the refereed proceedings of the 19th International Conference on Artificial Neural Networks, ICANN 2009, held in Limassol, Cyprus, in September 2009.

The 200 revised full papers presented were carefully reviewed and selected from more than 300 submissions. The first volume is divided in topical sections on learning algorithms; computational neuroscience; hardware implementations and embedded systems;  self organization; intelligent control and adaptive systems; neural and hybrid architectures; support vector machine; and recurrent neural network.