Application of Artificial Neural Networks in Particle Physics -- Evolutionary computation — History, status, and perspectives -- Temporal structure of cortical activity -- SEE-1 — A vision system for use in real world environments -- Towards integration of nerve cells and silicon devices -- Unifying perspectives on neuronal codes and processing -- Visual recognition based on coding in temporal cortex: Analysis of pattern configuration and generalisation across viewing conditions without mental rotation -- A novel encoding strategy for associative memory -- Autoassociative memory with high storage capacity -- Information efficiency of the associative net at arbitrary coding rates -- Efficient learning in sparsely connected Boltzmann machines -- Incorporating invariances in support vector learning machines -- Estimating the reliability of neural network classifications -- Bayesian inference of noise levels in regression -- Complexity reduction in probabilistic neural networks -- Asymptotic complexity of an RBF NN for correlated data representation -- Regularization by early stopping in single layer perceptron training -- Clustering in weight space of feedforward nets -- Learning curves of on-line and off-line training -- Learning structure with Many-Take-All networks -- Dynamic feature linking in stochastic networks with short range interactions -- Collective dynamics of a system of adaptive velocity channels -- Local linear model trees for on-line identification of time-variant nonlinear dynamic systems -- Nonparametric data selection for improvement of parametric neural learning: A cumulant-surrogate method -- Prediction of mixtures -- Learning dynamical systems produced by recurrent neural networks -- Purely local neural Principal Component and Independent Component Learning -- How fast can neuronal algorithms match patterns? -- An annealed ‘neural gas’ network for robust vector quantization -- Associative completion and investment learning using PSOMs -- GTM: A principled alternative to the Self-Organizing Map -- Creating term associations using a hierarchical ART architecture -- Architecture selection through statistical sensitivity analysis -- Regression by topological map: Application on real data -- Signal processing by neural networks to create “virtual” sensors and model-based diagnostics -- Development of an advisory system based on a neural network for the operation of a coal fired power plant -- Blast furnace analysis with neural networks -- Diagnosis tools for telecommunication network traffic management -- Adaptive saccade control of a Binocular Head with Dynamic Cell Structures -- Learning fine motion by using the Hierarchical Extended Kohonen Map -- Subspace dimension selection and averaged learning subspace method in handwritten digit classification -- A dual route neural net approach to grapheme-to-phoneme conversion -- Separating EEG spike-clusters in epilepsy by a growing and splitting net -- Optimal texture feature selection for the co-occurrence map -- Comparison of view-based object recognition algorithms using realistic 3D models -- Color-calibration of a robot vision system using self-organizing feature maps -- Neural network model for maximum ozone concentration prediction -- Very large two-level SOM for the browsing of newsgroups -- Automatic Part-Of-Speech tagging of Thai corpus using neural networks -- Reproducing a subjective classification scheme for atmospheric circulation patterns over the United Kingdom using a neural network -- Two gradient descent algorithms for blind signal separation -- Classification rejection by prediction -- Application of Radial Basis Function Neural Networks to odour sensing using a broad specificity array of conducting polymers -- A hybrid object recognition architecture -- Robot learning in analog neural hardware -- Visual gesture recognition by a modular neural system -- Tracking and learning graphs on image sequences of faces -- Neural network model recalling spatial maps -- Neural field dynamics for motion perception -- Analytical technique for deriving connectionist representations of symbol structures -- Modeling human word recognition with sequences of artificial neurons -- A connectionist variation on inheritance -- Mapping of multilayer perceptron networks to partial tree shape parallel neurocomputer -- Linearly expandable partial tree shape architecture for parallel neurocomputer -- A high-speed scalable CMOS current-mode Winner-Take-All network -- An architectural study of a massively parallel processor for convolution-type operations in complex vision tasks -- FPGA implementation of an adaptable-size neural network -- Extraction of coherent information from non-overlapping receptive fields -- Cortico-tectal interactions in the cat visual system -- Detecting and measuring higher order synchronization among neurons: A Bayesian approach -- Analyzing the formation of structure in high-dimensional Self-Organizing Maps reveals differences to feature map models -- Precise restoration of cortical orientation maps explained by hebbian dynamics of geniculocortical connections -- Modification of Kohonen's SOFM to simulate cortical plasticity induced by coactivation input patterns -- Cortical map development driven by spontaneous retinal activity waves -- Simplifying neural networks for controlling walking by exploiting physical properties -- Saccade control through the collicular motor map: Two-dimensional neural field model -- Plasticity of neocortical synapses enables transitions between rate and temporal coding -- Controlling the speed of synfire chains -- Temporal compositional processing by a DSOM hierarchical model -- A genetic model and the Hopfield networks -- Desaturating coefficient for projection learning rule -- Getting more information out of SDM -- Using a general purpose meta neural network to adapt a parameter of the quickpropagation learning rule -- Unsupervised learning of the minor subspace -- A unification of Genetic Algorithms, Neural Networks and Fuzzy Logic: The GANNFL Approach -- Active learning of the generalized high-low-game -- Optimality of pocket algorithm -- Improvements and extensions to the constructive algorithm CARVE -- Annealed RNN learning of finite state automata -- A hierarchical learning rule for independent component analysis -- Improving neural network training based on Jacobian rank deficiency -- Neural networks for exact constrained optimization -- Capacity of structured multilayer networks with shared weights -- Optimal weight decay in a perceptron -- Bayesian regularization in constructive neural networks -- A nonlinear discriminant algorithm for data projection and feature extraction -- A modified spreading algorithm for autoassociation in weightless neural networks -- Analysis of multi-fluorescence signals using a modified Self-Organizing Feature Map -- Visualizing similarities in high dimensional input spaces with a growing and splitting neural network -- A neural lexical post-processor for improved neural predictive word recognition -- Solving nonlinear MBPC through convex optimization: A comparative study using neural networks -- Combining statistical models for protein secondary structure prediction -- Using RBF-nets in rubber industry process control -- Towards autonomous robot control via self-adapting recurrent networks -- A hierarchical network for learning robust models of kinematic chains -- Context-based cognitive map learning for an autonomous robot using a model of cortico-hippocampal interplay -- An algorithm for bootstrapping the core of a biologically inspired motor control system -- Automatic recalibration of a space robot: An industrial prototype -- Population coding in cat visual cortex reveals nonlinear interactions as predicted by a neural field model -- Representing multidimensional stimuli on the cortex -- An analysis and interpretation of the oscillatory behaviour of a model of the granular layer

of the cerebellum -- The cerebellum as a “coupling machine” -- The possible function of dopamine in associative learning: A computational model -- Signatures of dynamic cell assemblies in monkey motor cortex -- Modelling speech processing and recognition in the auditory system with a three-stage architecture -- Binding — A proposed experiment and a model -- A reduced model for dendritic trees with active membrane -- Stabilizing competitive learning during on-line training with an anti-Hebbian weight modulation -- Neuro-biological bases for spatio-temporal data coding in artificial neural networks -- A spatio-temporal learning rule based on the physiological data of LTP induction in the hippocampal CA1 network -- Learning novel views to a single face image -- A parallel algorithm for depth perception from radial optical flow fields -- Comparing facial line drawings with gray-level images: A case study on PHANTOMAS -- Geometrically constrained optical flow estimation by an Hopfield neural network -- Serial binary addition with polynormally bounded weights -- Evaluation of the two different interconnection networks of the CNAPS neurocomputer -- Intrinsic and parallel performances of the OWE neural network architecture -- An analog CMOS neural network with on-chip learning and multilevel weight storage -- Exponential hebbian on-line learning implemented in FPGAs -- An information-theoretic measure for the classification of time series -- Transformation of neural oscillators -- Analysis of drifting dynamics with competing predictors -- Inverse dynamics controllers for robust control: Consequences for neurocontrollers -- A local connected neural oscillator network for pattern segmentation -- Approximation errors of state and output trajectories using recurrent neural networks -- Comparing self-organizing maps -- Nonlinear Independent Component Analysis by self-organizing maps -- Building nonlinear data models with self-organizing maps -- A parameter-free non-growing.

This book constitutes the refereed proceedings of the sixth International Conference on Artificial Neural Networks - ICANN 96, held in Bochum, Germany in July 1996. The 145 papers included were carefully selected from numerous submissions on the basis of at least three reviews; also included are abstracts of the six invited plenary talks. All in all, the set of papers presented reflects the state of the art in the field of ANNs. Among the topics and areas covered are a broad spectrum of theoretical aspects, applications in various fields, sensory processing, cognitive science and AI, implementations, and neurobiology.