Artificial Neural Networks - ICANN 2006 : 16th International Conference Athens, Greece, September 10-14, 2006 Proceedings, Part I

by Kollias, Stefanos; Stafylopatis, Andreas; Duch, Wlodzislaw; Oja, Erkki

• ISBN13: 9783540386254
• ISBN10: 3540386254
• Format: Paperback
• Copyright: 2006-10-15
• Publisher: Springer-Verlag New York Inc

Summary

The two volume set LNCS 4131 and LNCS 4132 constitutes the refereed proceedings of the 16th International Conference on Artificial Neural Networks, ICANN 2006, held in Athens, Greece, in September 2006.The 208 revised full papers presented were carefully reviewed and selected from 475 submissions. The 103 papers of the first volume are organized in topical sections on feature selection and dimension reduction for regression, learning algorithms, advances in neural network learning methods, ensemble learning, learning random neural networks and stochastic agents, hybrid architectures, self organization, connectionist cognitive science, cognitive machines, neural dynamics and complex systems, computational neuroscience, neural control, reinforcement learning and robotics applications, robotics, control, planning, as well as bio-inspired neural network on-chip implementation and applications. The second volume contains 105 contributions related to neural networks, semantic web technologies and multimedia analysis, bridging the semantic gap in multimedia machine learning approaches, signal and time series processing, data analysis, pattern recognition, visual attention algorithms and architectures for perceptional understanding and video coding, vision and image processing, computational finance and economics, neural computing in energy engineering, applications to biomedicine and bioinformatics, applications to security and market analysis, as well as real world applications.

Table of Contents

Dimensionality reduction based on ICA for regression problems	p. 1
A functional approach to variable selection in spectrometric problems	p. 11
The Bayes-optimal feature extraction procedure for pattern recognition using genetic algorithm	p. 21
Speeding up the wrapper feature subset selection in regression by mutual information relevance and redundancy analysis	p. 31
Effective input variable selection for function approximation	p. 41
Comparative investigation on dimension reduction and regression in three layer feed-forward neural network	p. 51
On-line learning with structural adaptation in a network of spiking neurons for visual pattern recognition	p. 61
Learning long term dependencies with recurrent neural networks	p. 71
Adaptive on-line neural network retraining for real life multimodal emotion recognition	p. 81
Time window width influence on dynamic BPTT(h) learning algorithm performance : experimental study	p. 93
Framework for the interactive learning of artificial neural networks	p. 103
Analytic equivalence of Bayes a posteriori distributions	p. 113
Neural network architecture selection : size depends on function complexity	p. 122
Competitive repetition-suppression (CoRe) learning	p. 130
Real-time construction of neural networks	p. 140
MaxMinOver regression : a simple incremental approach for support vector function approximation	p. 150
A variational formulation for the mutilayer perceptron	p. 159
Natural conjugate gradient training of mutilayer perceptrons	p. 169
Building ensembles of neural networks with class-switching	p. 178
K-separability	p. 188
Lazy training of radial basis neural networks	p. 198
Investigation of topographical stability of the concave and convex self-organizing map variant	p. 208
Alternatives to parameter selection for kernel methods	p. 216
Faster learning with overlapping neural assemblies	p. 226
Improved storage capacity of Hebbian learning attractor neural network with bump formations	p. 234
Error entropy minimization for LSTM training	p. 244
Can AdaBoost.M1 learn incrementally? : a comparison learn[superscript ++] under different combination rules	p. 254
Ensemble learning with local diversity	p. 264
A machine learning approach to define weights for linear combination of forecasts	p. 274
A game-theoretic approach to weighted majority voting for combining SVM classifiers	p. 284
Improving the expert networks of a modular multi-net system for pattern recognition	p. 293
Evaluating users' satisfaction in packet networks using random neural networks	p. 303
Random neural networks for the adaptive control of packet networks	p. 313
Hardware implementation of random neural networks with reinforcement learning	p. 321
G-networks and the modeling of adversarial agents	p. 330
Development of a neural net-based, personalized secure communication link	p. 340
Exact solutions for recursive principal components analysis of sequences and trees	p. 349
Active learning with the probabilistic RBF classifier	p. 357
Merging echo state and feedforward neural networks for time series forecasting	p. 367
Language and cognition integration through modeling field theory : category formation for symbol grounding	p. 376
A methodology for estimating the product life cycle cost using a hybrid GA and ANN model	p. 386
Using self-organizing maps to support video navigation	p. 396
Self-organizing neural networks for signal recognition	p. 406
An unsupervised learning rule for class discrimination in a recurrent neural network	p. 415
On the variants of the self-organizing map that are based on order statistics	p. 425
On the basis updating rule of adaptive-subspace self-organizing map (ASSOM)	p. 435
Composite algorithm for adaptive mesh construction based on self-organizing maps	p. 445
A parameter in the learning rule of SOM that incorporates activation frequency	p. 455
Nonlinear projection using geodesic distances and the neural gas network	p. 464
Contextual learning in the neurosolver	p. 474
A computational model for the effect of dopamine on action selection during Stroop test	p. 485
A neural network model of metaphor understanding with dynamic interaction based on a statistical language analysis	p. 495
Strong systematicity in sentence processing by an echo state network	p. 505
Modeling working memory and decision making using generic neural microcircuits	p. 515
A virtual machine for neural computers	p. 525
Machine cognition and the EC cognitive systems projects : now and in the future	p. 535
A complex neural network model for memory functioning in psychopathology	p. 543
Modelling working memory through attentional mechanisms	p. 553
A cognitive model of multi-objective multi-concept formation	p. 563
A basis for cognitive machines	p. 573
Neural model of dopaminergic control of arm movements in Parkinson's disease bradykinesia	p. 583
Occlusion, attention and object representations	p. 592
A forward / inverse motor controller for cognitive robotics	p. 602
A computational model for multiple goals	p. 612
Detection of a dynamical system attractor from spike train analysis	p. 623
Recurrent neural networks are universal approximators	p. 632
A discrete adaptive stochastic neural model for constrained optimization	p. 641
Quantum perceptron network	p. 651
Critical echo state networks	p. 658
Rapid correspondence finding in networks of cortical columns	p. 668
Adaptive thresholds for layered neural networks with synaptic noise	p. 678
Backbone structure of hairy memory	p. 688
Dynamics of citation networks	p. 698
Processing of information in synchroneously firing chains in networks of neurons	p. 710
Phase precession and recession with STDP and anti-STDP	p. 718
Visual pathways for detection of landmark points	p. 728
A model of grid cells based on a path integration mechanism	p. 740
Temporal processing in a spiking model of the visual system	p. 750
Accelerating event based simulation for multi-synapse spiking neural networks	p. 760
A neurocomputational model of an imitation deficit following brain lesion	p. 770
Temporal data encoding and SequenceLearning with spiking neural networks	p. 780
Optimal tuning of continual online exploration in reinforcement learning	p. 790
Vague neural network controller and its applications	p. 801
Parallel distributed profit sharing for PC cluster	p. 811
Feature extraction for decision-theoretic planning in partially observable environments	p. 820
Reinforcement learning with echo state networks	p. 830
Reward function and initial values : better choices for accelerated goal-directed reinforcement learning	p. 840
Nearly optimal exploration-exploitation decision thresholds	p. 850
Dual adaptive ANN controllers based on Wiener models for controlling stable nonlinear systems	p. 860
Online stabilization of chaotic maps via support vector machines based generalized predictive control	p. 868
Morphological neural networks and vision based mobile robot navigation	p. 878
Position control based on static neural networks of anthropomorphic robotic fingers	p. 888
Learning multiple models of non-linear dynamics for control under varying contexts	p. 898
A study on optimal configuration for the mobile manipulator : using weight value and mobility	p. 908
VSC perspective for neurocontroller tuning	p. 918
A neural network module with pretuning for search and reproduction of input-output mapping	p. 928
Physical mapping of spiking neural networks models on a bio-inspired scalable architecture	p. 936
A time multiplexing architecture for inter-neuron communications	p. 944
Neuronal cell death and synaptic pruning driven by spike-timing dependent plasticity	p. 953
Effects of analog-VLSI hardware on the performance of the LMS algorithm	p. 963
A portable electronic nose (E-nose) system based on PDA	p. 974
Optimal synthesis of Boolean functions by threshold functions	p. 983
Pareto-optimal noise and approximation properties of RBF networks	p. 993
Table of Contents provided by Blackwell. All Rights Reserved.