Artificial Neural Networks and Machine Learning - ICANN 2012 [electronic resource] : 22nd International Conference on Artificial Neural Networks, Lausanne, Switzerland, September 11-14, 2012, Proceedings, Part II / edited by Alessandro E. P. Villa, Włodzisław Duch, Péter Érdi, Francesco Masulli, Günther Palm.

Complex-Valued Multilayer Perceptron Search Utilizing Eigen Vector Descent and Reducibility -- Theoretical Analysis of Function of Derivative Term in On-Line Gradient Descent Learning -- Some Comparisons of Networks with Radial and Kernel -- Multilayer Perceptron for Label Ranking -- Electricity Load Forecasting: A Weekday-Based -- Adaptive Exploration Using Stochastic Neurons -- Comparison of Long-Term Adaptivity for Neural Networks -- Simplifying ConvNets for Fast Learning -- A Modified Artificial Fish Swarm Algorithm for the Optimization of Extreme Learning Machines -- Robust Training of Feedforward Neural Networks Using Combined Online/Batch Quasi-Newton Techniques -- Estimating a Causal Order among Groups of Variables in Linear Models -- Training Restricted Boltzmann Machines with Multi-tempering: Harnessing Parallelization -- A Computational Geometry Approach for Pareto-Optimal Selection of Neural Networks -- Learning Parameters of Linear Models in Compressed Parameter Space -- Control of a Free-Falling Cat by Policy-Based Reinforcement Learning -- Gated Boltzmann Machine in Texture Modeling -- Neural PCA and Maximum Likelihood Hebbian Learning on the GPU -- Construction of Emerging Markets Exchange Traded Funds Using Multiobjective Particle Swarm Optimisation -- The Influence of Supervised Clustering for RBFNN Centers Definition: A Comparative Study -- Nested Sequential Minimal Optimization for Support Vector Machines -- Random Subspace Method and Genetic Algorithm Applied to a LS-SVM Ensemble -- Text Recognition in Videos Using a Recurrent Connectionist Approach -- An Investigation of Ensemble Systems Applied to Encrypted and Cancellable Biometric Data -- New Dynamic Classifiers Selection Approach for Handwritten Recognition -- Vector Perceptron Learning Algorithm Using Linear Programming -- TrueSkill-Based Pairwise Coupling for Multi-class Classification -- Analogical Inferences in the Family Trees Task: A Review -- An Efficient Way of Combining SVMs for Handwritten Digit Recognition -- Comparative Evaluation of Regression Methods for 3D-2D Image Registration -- A MDRNN-SVM Hybrid Model for Cursive Offline Handwriting Recognition -- Extraction of Prototype-Based Threshold Rules Using Neural Training Procedure -- Instance Selection with Neural Networks for Regression Problems -- A New Distance for Probability Measures Based on the Estimation of Level Sets -- Low Complexity Proto-Value Function Learning from Sensory Observations with Incremental Slow Feature Analysis -- Improving Neural Networks Classification through Chaining -- Feature Ranking Methods Used for Selection of Prototypes -- A "Learning from Models" Cognitive Fault Diagnosis System -- Improving ANNs Performance on Unbalanced Data with an AUC-Based Learning Algorithm -- Learning Using Privileged Information in Prototype Based Models -- A Sparse Support Vector Machine Classifier with Nonparametric Discriminants -- Training Mahalanobis Kernels by Linear Programming -- Correntropy-Based Document Clustering via Nonnegative Matrix Factorization -- SOMM - Self-Organized Manifold Mapping -- Self-Organizing Map and Tree Topology for Graph Summarization -- Variable-Sized Kohonen Feature Map Probabilistic Associative Memory -- Learning Deep Belief Networks from Non-stationary Streams -- Separation and Unification of Individuality and Collectivity and Its Application to Explicit Class Structure in Self-Organizing Maps -- Autoencoding Ground Motion Data for Visualisation -- Examining an Evaluation Mechanism of Metaphor Generation with Experiments and Computational Model Simulation -- Pairwise Clustering with t-PLSI -- Selecting β-Divergence for Nonnegative Matrix Factorization by Score Matching -- Neural Networks for Proof-Pattern Recognition -- Using Weighted Clustering and Symbolic Data to Evaluate Institutes Scientific Production -- Comparison of Input Data Compression Methods in Neural Network Solution of Inverse Problem in Laser Raman Spectroscopy of Natural Waters -- New Approach for Clustering Relational Data Based on Relationship and Attribute Information -- Comparative Study on Information Theoretic Clustering and Classical Clustering Algorithms -- Text Mining for Wellbeing: Selecting Stories Using Semantic and Pragmatic Features -- Hybrid Bilinear and Trilinear Models for Exploratory Analysis of Three-Way Poisson Counts -- and Machine Learning Algorithms -- Rademacher Complexity and Structural Risk Minimization: An Application to Human Gene Expression Datasets -- Using a Support Vector Machine and Sampling to Classify Compounds as Potential Transdermal Enhancers -- The Application of Gaussian Processes in the Predictions of Permeability across Mammalian Membranes -- Protein Structural Blocks Representation and Search through Unsupervised NN -- Evolutionary Support Vector Machines for Time Series Forecasting -- Learning Relevant Time Points for Time-Series Data in the Life Sciences -- A Multivariate Approach to Estimate Complexity of FMRI Time Series -- Neural Architectures for Global Solar Irradiation and Air Temperature Prediction -- Sparse Linear Wind Farm Energy Forecast -- Diffusion Maps and Local Models for Wind Power Prediction -- A Hybrid Model for S&P500 Index Forecasting.