Icann '94

Contents, Volume 1.- 1 * Neurobiology.- Why bright Kanizsa squares look closer: consistency of segmentations and surfaces in 3-D vision.- Spatial pooling and perceptual framing by synchronizing cortical dynamics.- Vertebrate retina: sub-sampling and aliasing effects can explain colour-opponent and colour constancy phenomena.- RETINA: a model of visual information processing in the retinal neural network.- The influence of the inhomogeneous dendritic field size of the retinal ganglion cells on the fixation.- Top-down interference in visual perception.- Dynamic vision system: modeling the prey recognition of common toads Bufo bufo.- Emergence of long range order in maps of orientation preference.- Oriented ocular dominance bands in the self-organizing feature map.- How to use non-visual information for optic flow processing in monkey visual cortical area MSTd.- A learning rule for self-organization of the velocity selectivity of directionally selective cells.- Motion analysis with recurrent neural nets.- Self-organizing a behaviour-oriented interpretation of objects in active-vision.- Hybrid methods for robust irradiance analysis and 3-D shape reconstruction from images.- A parallel algorithm for simulating color perception.- Positional competition in the BCS.- A computational model for texton-based pre attentive texture segmentation.- Hopfield neural network for motion estimation and interpretation.- Phase interactions between place cells during movement.- Self-organization of an equilibrium-point motor controller.- Study of a Purkinje unit as a basic oscillator of the cerebellar cortex.- Compartmental interaction in the granular layer of the cerebellum.- Modeling biologically relevant temporal patterns.- A model of the baroreceptor reflex neural network.- Modelization of vestibulo-ocular reflex (VOR) and motion sickness prediction.- Kernel correlations of movements in neural network.- Analysis of the golf swing from weight-shift using neural networks.- Dry electrophysiology: an approach to the internal representation of brain functions through artificial neural networks.- ANNs and MAMFs: transparency or opacity?.- Collective brain as dynamical system.- Temporal pattern dependent spatial-distribution of LTP in the hippocampal CAl area studied by an optical imaging method.- Synchronization-based complex model neurons.- Synchronization of integrate-and-fire neurons with delayed inhibitory lateral connections.- Complex patterns of oscillations in a neural network model with activity-dependent outgrowth.- Learning and the thalamic-NRT-cortex system.- Resetting the periodic activity of Hydra at a fixed phase.- Integral equations in compartmental model neurodynamics.- Hysteresis in a two neuron-network: basic characteristics and physiological implications.- Cooperation within networks of cortical automata based networks.- Anisotropic correlation properties in the spatial structure of cortical orientation maps.- 2 * Mathematical Model.- Application of neural network and fuzzy logic in modelling and control of fermentation processes.- Neural networks for the processing of fuzzy sets.- Human sign recognition using fuzzy associative inference system.- Bayesian properties and performances of adaptive fuzzy systems in pattern recognition problems.- The representation of human judgement by using fuzzy techniques.- Fuzzy logic versus neural network technique in an identification problem.- Phoneme recognition with hierarchical self organised neural networks and fuzzy systems - A Case Study.- Neuronal network models of the mind.- The consciousness of a neural state machine.- Forward reasoning and Caianiello's nets.- An ANN model of anaphora: implications for nativism.- The spatter code for encoding concepts at many levels.- Learning in hybrid neural models.- A connectionist model for context effects in the picture-word interference task.- Inductive inference with recurrent radial basis function networks.- Neural networks as a paradigm for knowledge elicitation.- Unsupervised detection of driving states with hierarchical self organizing maps.- Using simulated annealing to train relaxation labeling processes.- A neural model for the execution of symbolic motor programs.- Evolution of typed expressions describing artificial nervous systems.- BAR: a connectionist model of bilingual access representations.- An architecture for image understanding by symbol and pattern integration.- Encoding conceptual graphs by labeling RAAM.- Hybrid system for ship detection in radar images.- Using ART2 and BP co-operatively to classify musical sequences.- Forecasting using constrained neural networks.- The evaluations of environmental impact: cooperative systems.- What generalizations of the self-organizing map make sense?.- A novel approach to measure the topology preservation of feature maps.- Self-Organized learning of 3 dimensions.- A model of fast and reversible representational plasticity using Kohonen mapping.- Multiple self-organizing neural networks with the reduced input dimension.- Adaptive modulation of receptive fields in self-organizing networks.- About the convergence of the generalized Kohonen algorithm.- Reordering transitions in self-organized feature maps with short-range neighbourhood.- Speeding-up self-organizing maps: the quick reaction.- Dynamic extensions of self-organizing maps.- Feature selection with self-Organizing feature map.- Unification of complementary feature map models.- Considerations of geometrical and fractal dimension of SOM to get better learning results.- On the ordering conditions for self-organising maps.- Representation and identification of fault conditions of an anaesthesia system by means of the self-organizing map.- Sensor arrays and self-organizing maps for odour analysis in artificial olfactory systems.- A self-organising neural network for the travelling salesman problem that is competitive with simulated annealing.- Learning attractors as a stochastic process.- Nominal color coding of classified images by Hopfield networks.- Does terminal attractor backpropagation guarantee global optimization?.- Learning and retrieval in attractor neural networks with noise above saturation.- A method of teaching a neural network to generate vector fields for a given attractor.- Recurrent neural networks with delays.- Eman: equivalent mass attraction network.- Analysis of an unsupervised indirect feedback network.- Hopfield energy of random nets.- Multiple cueing of an associative net.- Programmable mixed implementation of the Boltzmann machine.- The influence of response functions in analogue attractor neural networks.- Improvement of learning in recurrent networks by substituting the sigmoid activation function.- Attractor properties of recurrent networks with generalising boolean nodes.- On a class of Hopfield type neural networks for associative memory.- Storage capacity of associative random neural networks.- A generalized bidirectional associative memory with a hidden orthogonal layer.- Finding correspondences between smoothly deformable contours by means of an elastic neural network.- Minimization of number of connections in feedback networks.- An efficient method of pattern storage in the hopfield net.- Recursive learning in recurrent neural networks with varying architecture.- Pruning in recurrent neural networks.- Making hard problems linearly separable - Incremental radial basis function approaches.- 'Partition of unity' RBF networks are universal function approximators.- Optimal local estimation of RBF parameters.- Acceleration of Gaussian radial basis function networks for function-approximation.- Uniqueness of functional representations by Gaussian basis function networks.- A dynamic mixture of Gaussians neural network for sequence classification.- Hierarchical mixtures of experts and the EM algorithm.- Outline of a linear neural network and applications.- Numerical experiments on the information criteria for layered feedforward neural nets.- Quantifying a critical training set size for generalization and overfitting using teacher neural networks.- Formal representation of neural networks.- Training-dependent measurement.- Genetic algorithms as optimisers for feedforward neural networks.- Selecting a critical subset of given examples during learning.- On the circuit complexity of feedforward neural networks.- Avoiding local minima by a classical range expansion algorithm.- Learning time series by neural networks.- The error absorption for fitting an under-fitting (skeleton) net.- Fast backpropagation using modified sigmoidal functions.- Input contribution analysis in a double input layered neural network.- A unified approach to derive gradient algorithms for arbitrary neural network structures.- Interpretation of BP-trained net outputs.- Fluctuated-threshold effect in multilayered neural network.- On the properties of error functions that affect the speed of backpropagation learning.- Neural network optimization for good generalization performance.- Block-recursive least squares technique for training multilayer perceptrons.- Neural networks for iterative computation of inverse functions.- Cascade correlation convergence theorem.- Optimal weight Initialization for neural networks.- Neural nets with superlinear VC-dimension.- A randomised distributed primer for the updating control on anonymous ANNs.- Catastrophic interference in learning processes by neural networks.- Systematicity in IH-analysis.- Integrating distance measure and inner product neurons.- Teaching by showing in Kendama based on optimization principle.- From coarse to fine: a novel way to train neural networks.- Learning the activation function for the neurons in neural networks.- Projection learning and graceful degradation.- Learning with zero error in feedforward neural networks.- Robustness of Hebbian and anti-Hebbian learning.- Computational experiences of new direct methods for the on-line training of MLP-networks with binary outputs.- Optimising local Hebbian learning: use the o-rule.- Efficient neural net ?-?-evaluators.- A parallel algorithm for a dynamic eta/ alpha estimation in backpropagation learning.- Dynamic pattern selection: effectively training backpropagation neural networks.- A learning rule which implicitly stores training history in weights.- A comparison study of unbounded and real-valued reinforcement associative reward-penalty algorithms.- To swing up an inverted pendulum using stochastic real-valued reinforcement learning.- Efficient reinforcement learning strategies for the pole balancing problem.- Reinforcement learning in Kohonen feature maps.- CMAC manipulator control using a reinforcement learned trajectory planner.- A fast reinforcement learning paradigm with application to CMAC control systems.- Information geometry and the EM algorithm.- SSM: a statistical stepwise method for weight elimination.- Computing the probability density in connectionist regression.- Estimation of conditional densities: a comparison of neural network approaches.- Regularizing stochastic Pott neural networks by penalizing mutual information.- Least mean squares learning algorithm in self referential linear stochastic models.- An approximation network with maximal transinformation.- Extended functionality for probabilistic RAM neurons.- Statistical biases in backpropagation learning.- An approximation of nonlinear canonical correlation analysis by multilayer perceptrons.- Information minimization to improve generalization performance.- Learning and interpretation of weights in neural networks.- Variable selection with optimal cell damage.- Comparison of constructive algorithms for neural networks.- Task decomposition and correlations in growing artificial Neural networks.- XNeuroGene: a system for evolving artificial neural networks.- Incremental training strategies.- Modular object-oriented neural network simulators and topology generalizations.- Gradient-based adaptation of Network Structure.- A connectionist model using multiplexed oscillations and synchrony to enable dynamic connections.- Some results on correlation dimension of time series generated by a network of phase oscillators.- Towards the application of networks with synchronized oscillatory dynamics in vision.- New impulse neuron circuit for oscillatory neural networks.- Adaptive topologically distributed encoding.- On-line learning with momentum for nonlinear learning rules.- Constructive neural network algorithm for approximation of multivariable function with compact support.- A Hebb-like learning rule for cell assemblies formation.- CARVE - a constructive algorithm for real valued examples.- A supervised learning rule for the single spike model.- Comparative bibliography of ontogenic neural networks.- Controlled growth of cascade correlation nets.