Artificial Neural Networks - ICANN 2007

by de Sa, Joaquim Marques; Alexandre, Luis A.; Duch, Wlodzislaw; Mandic, Danilo P.

• ISBN13: 9783540746898
• ISBN10: 3540746897
• Format: Paperback
• Copyright: 2007-10-12
• Publisher: Springer-Verlag New York Inc

Summary

This book is the first of a two-volume set that constitutes the refereed proceedings of the 17th International Conference on Artificial Neural Networks, ICANN 2007, held in Porto, Portugal, September 2007. Coverage includes advances in neural network learning methods, advances in neural network architectures, neural dynamics and complex systems, data analysis, evolutionary computing, agents learning, as well as temporal synchronization and nonlinear dynamics in neural networks.

Table of Contents

Learning Theory
Generalization Error of Automatic Relevance Determination	p. 1
On a Singular Point to Contribute to a Learning Coefficient and Weighted Resolution of Singularities	p. 11
Improving the Prediction Accuracy of Echo State Neural Networks by Anti-Oja's Learning	p. 19
Theoretical Analysis of Accuracy of Gaussian Belief Propagation	p. 29
Relevance Metrics to Reduce Input Dimensions in Artificial Neural Networks	p. 39
An Improved Greedy Bayesian Network Learning Algorithm on Limited Data	p. 49
Incremental One-Class Learning with Bounded Computational Complexity	p. 58
Estimating the Size of Neural Networks from the Number of Available Training Data	p. 68
A Maximum Weighted Likelihood Approach to Simultaneous Model Selection and Feature Weighting in Gaussian Mixture	p. 78
Estimation of Poles of Zeta Function in Learning Theory Using Pade Approximation	p. 88
Neural Network Ensemble Training by Sequential Interaction	p. 98
Improving Optimality of Neural Rewards Regression for Data-Efficient Batch Near-Optimal Policy Identification	p. 109
Advances in Neural Network Learning Methods
Structure Learning with Nonparametric Decomposable Models	p. 119
Recurrent Bayesian Reasoning in Probabilistic Neural Networks	p. 129
Resilient Approximation of Kernel Classifiers	p. 139
Incremental Learning of Spatio-temporal Patterns with Model Selection	p. 149
Accelerating Kernel Perceptron Learning	p. 159
Analysis and Comparative Study of Source Separation Performances in Feed-Forward and Feed-Back BSSs Based on Propagation Delays in Convolutive Mixture	p. 169
Learning Highly Non-separable Boolean Functions Using Constructive Feedforward Neural Network	p. 180
A Fast Semi-linear Backpropagation Learning Algorithm	p. 190
Improving the GRLVQ Algorithm by the Cross Entropy Method	p. 199
Incremental and Decremental Learning for Linear Support Vector Machines	p. 209
An Efficient Method for Pruning the Multilayer Perceptron Based on the Correlation of Errors	p. 219
Reinforcement Learning for Cooperative Actions in a Partially Observable Multi-agent System	p. 229
Input Selection for Radial Basis Function Networks by Constrained Optimization	p. 239
An Online Backpropagation Algorithm with Validation Error-Based Adaptive Learning Rate	p. 249
Adaptive Self-scaling Non-monotone BFGS Training Algorithm for Recurrent Neural Networks	p. 259
Some Properties of the Gaussian Kernel for One Class Learning	p. 269
Improved SOM Learning Using Simulated Annealing	p. 279
The Usage of Golden Section in Calculating the Efficient Solution in Artificial Neural Networks Training by Multi-objective Optimization	p. 289
Ensemble Learning
Designing Modular Artificial Neural Network Through Evolution	p. 299
Averaged Conservative Boosting: Introducing a New Method to Build Ensembles of Neural Networks	p. 309
Selection of Decision Stumps in Bagging Ensembles	p. 319
An Ensemble Dependence Measure	p. 329
Boosting Unsupervised Competitive Learning Ensembles	p. 339
Using Fuzzy, Neural and Fuzzy-Neural Combination Methods in Ensembles with Different Levels of Diversity	p. 349
Spiking Neural Networks
SpikeStream: A Fast and Flexible Simulator of Spiking Neural Networks	p. 360
Evolutionary Multi-objective Optimization of Spiking Neural Networks	p. 370
Building a Bridge Between Spiking and Artificial Neural Networks	p. 380
Clustering of Nonlinearly Separable Data Using Spiking Neural Networks	p. 390
Implementing Classical Conditioning with Spiking Neurons	p. 400
Advances in Neural Network Architectures
Deformable Radial Basis Functions	p. 411
Selection of Basis Functions Guided by the L2 Soft Margin	p. 421
Extended Linear Models with Gaussian Prior on the Parameters and Adaptive Expansion Vectors	p. 431
Functional Modelling of Large Scattered Data Sets Using Neural Networks	p. 441
Stacking MF Networks to Combine the Outputs Provided by RBF Networks	p. 450
Neural Network Processing for Multiset Data	p. 460
The Introduction of Time-Scales in Reservoir Computing, Applied to Isolated Digits Recognition	p. 471
Partially Activated Neural Networks by Controlling Information	p. 480
CNN Based Hole Filler Template Design Using Numerical Integration Techniques	p. 490
Impact of Shrinking Technologies on the Activation Function of Neurons	p. 501
Rectangular Basis Functions Applied to Imbalanced Datasets	p. 511
Qualitative Radial Basis Function Networks Based on Distance Discretization for Classification Problems	p. 520
A Control Approach to a Biophysical Neuron Model	p. 529
Integrate-and-Fire Neural Networks with Monosynaptic-Like Correlated Activity	p. 539
Multi-dimensional Recurrent Neural Networks	p. 549
FPGA Implementation of an Adaptive Stochastic Neural Model	p. 559
Neural Dynamics and Complex Systems
Global Robust Stability of Competitive Neural Networks with Continuously Distributed Delays and Different Time Scales	p. 569
Nonlinear Dynamics Emerging in Large Scale Neural Networks with Ontogenetic and Epigenetic Processes	p. 579
Modeling of Dynamics Using Process State Projection on the Self Organizing Map	p. 589
Fixed Points of the Abe Formulation of Stochastic Hopfield Networks	p. 599
Visualization of Dynamics Using Local Dynamic Modelling with Self Organizing Maps	p. 609
Comparison of Echo State Networks with Simple Recurrent Networks and Variable-Length Markov Models on Symbolic Sequences	p. 618
Data Analysis
Data Fusion and Auto-fusion for Quantitative Structure-Activity Relationship (QSAR)	p. 628
Cluster Domains in Binary Minimization Problems	p. 638
MaxSet: An Algorithm for Finding a Good Approximation for the Largest Linearly Separable Set	p. 648
Generalized Softmax Networks for Non-linear Component Extraction	p. 657
Stochastic Weights Reinforcement Learning for Exploratory Data Analysis	p. 668
Post Nonlinear Independent Subspace Analysis	p. 677
Estimation
Algebraic Geometric Study of Exchange Monte Carlo Method	p. 687
Solving Deep Memory POMDPs with Recurrent Policy Gradients	p. 697
Soft Clustering for Nonparametric Probability Density Function Estimation	p. 707
Vector Field Approximation by Model Inclusive Learning of Neural Networks	p. 717
Spectral Measures for Kernel Matrices Comparison	p. 727
A Novel and Efficient Method for Testing Non Linear Separability	p. 737
A One-Step Unscented Particle Filter for Nonlinear Dynamical Systems	p. 747
Spatial and Spatio-Temporal Learning
Spike-Timing-Dependent Synaptic Plasticity to Learn Spatiotemporal Patterns in Recurrent Neural Networks	p. 757
A Distributed Message Passing Algorithm for Sensor Localization	p. 767
An Analytical Model of Divisive Normalization in Disparity-Tuned Complex Cells	p. 776
Evolutionary Computing
Automatic Design of Modular Neural Networks Using Genetic Programming	p. 788
Blind Matrix Decomposition Via Genetic Optimization of Sparseness and Nonnegativity Constraints	p. 799
Meta Learning, Agents Learning
Meta Learning Intrusion Detection in Real Time Network	p. 809
Active Learning to Support the Generation of Meta-examples	p. 817
Co-learning and the Development of Communication	p. 827
Complex-Valued Neural Networks (Special Session)
Models of Orthogonal Type Complex-Valued Dynamic Associative Memories and Their Performance Comparison	p. 838
Dynamics of Discrete-Time Quaternionic Hopfield Neural Networks	p. 848
Neural Learning Algorithms Based on Mappings: The Case of the Unitary Group of Matrices	p. 858
Optimal Learning Rates for Clifford Neurons	p. 864
Solving Selected Classification Problems in Bioinformatics Using Multilayer Neural Network Based on Multi-Valued Neurons (MLMVN)	p. 874
Error Reduction in Holographic Movies Using a Hybrid Learning Method in Coherent Neural Networks	p. 884
Temporal Synchronization and Nonlinear Dynamics in Neural Networks (Special Session)
Sparse and Transformation-Invariant Hierarchical NMF	p. 894
Zero-Lag Long Range Synchronization of Neurons Is Enhanced by Dynamical Relaying	p. 904
Polynomial Cellular Neural Networks for Implementing the Game of Life	p. 914
Deterministic Nonlinear Spike Train Filtered by Spiking Neuron Model	p. 924
The Role of Internal Oscillators for the One-Shot Learning of Complex Temporal Sequences	p. 934
Clustering Limit Cycle Oscillators by Spectral Analysis of the Synchronisation Matrix with an Additional Phase Sensitive Rotation	p. 944
Control and Synchronization of Chaotic Neurons Under Threshold Activated Coupling	p. 954
Neuronal Multistability Induced by Delay	p. 963
Author Index	p. 973
Table of Contents provided by Ingram. All Rights Reserved.