ICANN-Program

Program by Topic

Biological Models

- Coding and Learning in Biology
- Cortical Maps and Receptive Fields

Theory

- Learning: Theory and Algorithms
- Signal Processing: Blind Source Separation, Vector Quantization, and Self-Organization

Applications

- Robotics, Adaptive Autonomous Agents, and Control
- Speech, Vision, and Pattern Recognition
- Prediction, Forecasting, and Identification

Implementations

- Analog and Digital Implementations


The page numbers refer to the ICANN'97 proceedings published by Springer, Lecture Notes in Computer Science Series

Coding and Learning in Biology

Invited Plenay Talk S6 (8.10 - 14h00)

Reward Responses of Dopamine Neurons: A Biological Reinforcement Signal

Schultz W. - p.3 ;

Invited Plenay Talk S21 (10.10. - 8h30)

The Information Content of Action Potential Trains - A Synaptic Basis

Markram H., Tsodyks M. - p.13 ;

S24, Invited Special Session: Brain Dynamics (10.10; 10h30-12.15)

Oral Presentations

Cortical Cell Assemblies, Laminar Interaction, and Thalamocortical Interplay

Miller R. - p.25 ;

Cross-Correlations in Sparsely Connected Recurrent Networks of Spiking Neurons

Brunel N. - p.31 ;

A Comparative Study of Pattern Detection Algorithm and Dynamical System Approach Using Simulated Spike Trains

Tetko I.V., Villa A.E.P. - p.37 ;

Spatio-Temporal Pattern Recognition with Neural Networks: Application to Speech

Rouat J. - p.43 ;

Noise in Integrate-and-Fire Models of Neuronal Dynamics

Lansky P., Lanska V. - p.49 ;

S14: Neural Coding (9.10; 10h30-12.15)

Oral Presentations

Coarse Coding Accounts for Improvement of Spatial Discrimination after Plastic Reorganization in Rats and Humans

Eurich C.W., Dinse H.R., Dicke U., Godde B., and Schwegler H. - p.55 ;

Analogue Resolution in a Model of the Schaffer Collaterals

Schultz S., Panzeri S., Treves A., and Rolls E.T. - p.61 ;

Modeling Networks with Linear (VLSI) Integrate-and-Fire Neurons

Mattia M., Fusi S. - p.67 ;

An Information-Theoretic Analysis of Temporal Coding Strategies by Spiking Central Neurons

Deco G., Schuermann B. - p.73 ;

Poster Spotlights

Correlation Coding in Stochastic Neural Networks

Ritz R., Sejnowski T.J. - p.79 ;

Two-Dimensional Hodgkin-Huxley Equations for Investigating a Basis of Pulse-Processing Neural Networks

Hirose A. - p.85 ;

Concurrent Parallel-Sequential Processing in Gamma Controlled Cortical-Type Networks of Spiking Neurones

Koerner E., Koerner U. - p.91 ;

A Noise-Robust Auditory Modelling Front End for Voiced Speech

Smith L.S. - p.97 ;

A Novelty Detector Using a Network of Integrate and Fire Neurons

Ho T.V., Rouat J. - p.103 ;

Derivation of Pool Dynamics from Microscopic Neuronal Models

Eggert J., van Hemmen J.L. - p.109 ;

S9: Synpatic Learning (8.10; 16h00 - 17h45)

Oral Presentations

How a Single Purkinje Cell Could Learn the Adaptive Timing of the Classically Conditioned Eye-Blink Response

Steuber V., Willshaw D.J. - p.115 ;

An Algorithm for Synaptic Modification Based on Exact Timing of Pre- and Post-Synaptic Action Potentials

Senn W., Tsodyks M., and Markram H. - p.121 ;

Modelling Plasticity in Rat Barrel Cortex Induced by One Spared Whisker

Benuskov`a L. - p.127 ;

Mathematical Analysis of Competition Between Sensory Ganglion Cells for Nerve Growth Factor in the Skin

Kohli R., Clarke P.G.H. - p.133 ;

Poster Spotlights

Competition Amongst Neurons for Neurotrophins

van Ooyen A., Willshaw D.J. - p.139 ;

Implementing Hebbian Learning in a Rank-based Neural Network

Samuelides M., Thorpe S., and Veneau E. - p.145 ;

A Model of Clipped Hebbian Learning in a Neocortical Pyramidal Cell

Graham B., Willshaw D. - p.151 ;

Hebbian Delay Adaptation in a Network of Integrate-and-Fire Neurons

Eurich C.W., Cowan J.D., and Milton J.G. - p.157 ;

Hippocampal Formation Trains Independent Components via Forcing Input Reconstruction

Lorincz A. - p.163 ;


Cortical Maps and Receptive Fields

S28: Invited Special Session: Maps and Receptive Fields in the Visual Cortex (10.10; 15h10-16h50)

Oral Presentations

Nature vs. Nurture in the Development of Tangential Connections and Functional Maps in the Visual Cortex

Loewel S., Schmidt K.E., and Singer W. - p.171 ;

Geometric Relationships Between Feature Maps in Cat Visual Cortex

Huebener M., Shoham D., Schulze S., Brandle G., Grinvald A., and Bonhoeffer T. - p.177 ;

A Linear Hebbian Model for the Development of Spatiotemporal Receptive Fields of Simple Cells

Wimbauer S., Wenisch O., van Hemmen J.L. - p.183 ;

Synapse Clustering Can Drive Simultaneous ON-OFF and Ocular- Dominance Segregation in a Model of Area 17

Stetter M., Lang E.W., and Obermayer K. - p.189 ;

Must Pinwheels Move During Visual Development?

Wolf F., Geisel T. - p.195 ;

S19: Neural Maps (9.10; 15h00 - 16h45)

Oral Presentations

Extending the TRN Model in a Biologically Plausible Way

Frisone F., Perico L., and Morasso P.G. - p.201 ;

SOM-Model for the Development of Oriented Receptive Fields and Orientation Maps from Non-Oriented ON-center OFF-center Inputs

Brockmann D., Bauer H.U., Riesenhuber M., and Geisel T. - p.207 ;

On the Anatomical Basis of Field Size, Contrast, Sensitivity, and Orientation Selectivity in Macaque Striate Cortex: A Model Study

Bauer U., Adorjan P., Scholz M., Levitt J.B., Lund J.S., Obermayer K. - p.213} -

Statistics of Natural and Urban Images

Ziegaus C., Lang E.W. - p.219 ;

Poster Spotlights

A CBL Network Model with Intracortical Plasticity and Natural Image Stimuli

Burger T., Lang, E.W. - p.225 ;

Geometry of Orientation Preference Map Determines Nonclassical Receptive Field Properties

Ernst U., Pawelzik K., Wolf F., and Geisel T. - p.231 ;

A Model for Orientation Tuning and Contextual Effects of Orientation Selective Receptive Fields

Bartsch H., Stetter M., and Obermayer K. - p.237 ;

Objective Functions for Neural Map Formation

Wiskott L., Sejnowski T.J. - p.243 ;

Relative Time Scales in the Self-Organization of Pattern Classification: From One-Shot to Statistical Learning

Kopecz K., Mohraz K. - p.249 ;

Realization of Geometric Illusions and Geometry of Visual Space with Neural Networks

Chao J., Miyata Y., Yoshida S. - p.255 ;


Learning: Theory and Algorithms

Invited Plenay Talk S1 (8.10. - 8h30)

The Support Vector Method

Vapnik V.N. - p.263 ;

Invited Plenay Talk S6 (8.10. 14h00)

On the Significance of Markov Decision Processes

Sutton R.S. - p.273 ;

S3: Learning I (8.10; 10h30-12.15)

Oral Presentations

Economical Reinforcement Learning for Non Stationary Problems

Chatenet N., Bersini H. - p.283 ;

A Double Gradient Algorithm to Optimize Regularization

Czernichow T. - p.289 ;

Global Least-Squares vs. EM Training for the Gaussian Mixture of Experts

Bradshaw N.P., Duch^ateau A., and Bersini H. - p.295 ;

Accellerated Learning in Boltzmann Machines Using Mean Field Theory

Kappen H.J., Rodriguez F.B. - p.301 ;

Poster Spotlights

Adaptive Online Learning for Nonstationary Problems

Boes S. - p.307 ;

Weight Discretization due to Optical Constraints and its Influence on the Generalization Abilities of a Simple Perceptron

Aboukassen M., Schwember S., Noehte S., and Maenner R. - p.313 ;

Wavelet Frames Based Estimator

Soltani S., Canu S., Boichu D., and Grandvalet Y. - p.319 ;

A Spatio-Temporal Perceptron for on-Line Handwritten Character Recognition

Mozayyani N., Vaucher G. - p.325 ;

Learning Oscillations Using Adaptive Control

Weiss M.G. - p.331 ;

Creation of Neural Networks Based on Developmental and Evolutionary Principles

Eggenberger P. - p.337 ;

S28: Learning II (10.10; 15h10-16h50)

Oral Presentations

A Boosting Algorithm for Regression

Bertoni A., Campadelli P., and Parodi M. - p.343 ;

Combining Regularized Neural Networks

Taniguchi M., Tresp V. - p.349 ;

Making Stochastic Networks Deterministic

Rueger S.M. - p.355 ;

Unsupervised Learning in Networks of Spiking Neurons Using Temporal Coding

Ruf B., Schmitt M. - p.361 ;

Experiments on Regularizing MLP Models with Background Knowledge

Selonen A., Lampinen J. - p.367 ;

S27: Kernel Based Approaches (10.10; 15h10-16h50)

Oral Presentations

Elliptical Basis Function Networks for Classification Tasks

Gutjahr S., Feist J. - p.373 ;

Probabilistic Neural Networks with Rotated Kernel Functions

Galleske I., Castellanos J. - p.379 ;

Statistical Control of RBF-like Networks for Classification

Jankowski N., Kadirkamanathan V. - p.385 ;

Improving RBF Networks by Feature Selection Approach EUBAFES

Scherf M., Brauer W. - p.391 ;

Polynomial Classifiers and Support Vector Machines

Graf I., Kressel U., and Franke J. - p.397 ;

Unique Representations of Dynamical Systems Produced by Recurrent Neural Networks

S12: Recurrent Networks (9.10; 10h30-12.15)

Oral Presentations

Kimura M., Nakano R. - p.403 ;

Generalization of Elman Networks

Hammer B. - p.409 ;

Designing Neural Networks by a Combination of Structural Learning and Genetic Algorithms

Ishikawa M., Nishino K. - p.415 ;

A Recurrent Self-Organizing Map for Temporal Sequence Processing

Varsta M., Millan J. del R., Heikkonen J. - p.421 ;

Poster Spotlights

An Extended Elman Net for Modeling Time Series

Stagge P., Sendhoff B. - p.427 ;

Recurrent Associative Memory Network of Nonlinear Coupled Oscillators

Kuzmina M.G., Manykin E.E., and Surina I.I. - p.433 ;

A Layered Recurrent Neural Network for Feature Grouping

Wersing H., Steil J.J., and Ritter H. - p.439 ;

A Multilayer Real-Time Recurrent Learning Algorithm for Improved Convergence

Meert K., Ludik J. - p.445 ;

Increasing the Capacity of a Hopfield Network without Sacrificing Functionality

Storkey A. - p.451 ;

A Novel Associative Network Accommodating Pattern Deformation

Wang H., Bell D. - p.457 ;

S17: Perceptrons and Classification (9.10; 15h00 - 16h45)

Oral Presentations

Adaptive Noise Injection for Input Variables Relevance Determination

Grandvalet Y., Canu S. - p.463 ;

Input Selection with Partial Retraining

van de Laar P., Gielen S., and Heskes T. - p.469 ;

On the Complexity of Recognizing Iterated Differences of Polyhedra

Mayoraz E. - p.475 ;

Optimal Linear Regression on Classifiers Outputs

Guermeur Y., d'Alch'e-Buc F., and Gallinari P. - p.481 ;

Poster Spotlights

Learning Verification in Multilayer Neural Networks

Qu'elavoine R., Nocera P. - p.487 ;

Design of a Fault Tolerant Multilayer Perceptron with a Desired Level of Robustness

Kwon O.J., Bang S.Y. - p.493 ;

Mixtures of Experts Estimate a Posteriori Probabilities

Moerland P. - p.499 ;

Admissibility and Optimality of the Cascade-Correlation Algorithm

Doering A., Galicki M, and Witte H. - p.505 ;

The Effective VC Dimension of the n-tuple Classifier

Bradshaw N.P. - p.511 ;


Signal Processing: Blind Source Separation, Vector Quantization, and Self-Organization

Invited Plenay Talk S1 (8.10. - 9.15)

From Neural Principal Components to Neural Independent Components

Oja E., Karhunen J., and Hyvarinen A. - p.519 ;

S2: Signal Processing (8.10; 10h30-12.15)

Oral Presentations

Entropy Optimization - Application to Blind Source Separation

Taleb A., Jutten C. - p.529 ;

Improving the Performance of Infomax Using Statistical Signal Processing Techniques

Koehler B.U., Lee T.W., and Orglmeister R. - p.535 ;

A Maximum Likelihood Approach to Nonlinear Blind Source Separation

Pajunen P., Karhunen J. - p.541 ;

A Perceptron-Based Approach to Piecewise Linear Modeling with an Application to Time Series

Mattavelli M., Amaldi E., and Vesin J.M. - p.547 ;

Poster Spotlights

Local Independent Component Analysis by the Self-Organizing Map

Oja E., Valkealahti K. - p.553 ;

Model Breaking Detection Using Independent Component Classifier

Linares G., Nocera P., and Meloni H. - p.559 ;

Neural Network Based Processing for Smart Sensors Arrays

Paraschiv-Ionescu A., Jutten C., and Bouvier G. - p.565 ;

Application of the MEC Network to Principal Component Analysis and Source Separation

Fiori S., Uncini A., and Piazza F. - p.571 ;

Semi-Blind Source Parameter Separation

Joutsensalo J. - p.577 ;

Kernel Principal Component Analysis

Schoelkopf B., Smola A.J., and Mueller K.R. - p.583 ;

S22: Dimension Reduction (10.10; 10h30-12.15)

Oral Presentations

An Empirical Comparison of Dimensionality Reduction Techniques for Pattern Classification

Balachander T., Kothari R., and Cualing H. - p.589 ;

Topology Representing Networks for Intrinsic Dimensionality Estimation

Bruske J., Sommer G. - p.595 ;

SOM Based Visualization in Data Analysis

Hakkinen E., Koikkalainen P. - p.601 ;

ARTMAP-DS: Pattern Discrimination by Discounting Similarities

Carpenter G.A., Wilson F.D.M. - p.607 ;

S7: Self Organization (8.10; 16h00 - 17h45)

Oral Presentations

A Self-Organizing Network that Can Follow Non-Stationary Distributions

Fritzke B. - p.613 ;

Phase Transitions in Soft Topographic Vector Quantization

Burger M., Graepel T., and Obermayer K. - p.619 ;

Vector Quantization by Optimal Neural Gas

Herrmann M., Villmann T. - p.625 ;

Convergences of the Kohonen Maps: a Dynamical System Approach

Fort J-.C., Pag`es G. - p.631 ;

Poster Spotlights

Local Subspace Classifier

Laaksonen J. - p.637 ;

Asymptotic Distributions Associated to Unsupervised Oja's Learning Equation

Delmas J.-P. - p.643 ;

The Probabilistic Growing Cell Structures Algorithm

Vlassis N.A., Dimopoulos A., and Papakonstantinou G. - p.649 ;

Unsupervised Coding with LOCOCODE

Hochreiter S., Schmidhuber J. - p.655 ;

Wave Propagation in Self-Organizing Feature Maps as a Means for the Representation of Temporal Sequences

Dobrzewski B., Ruwish D., and Bode M. - p.661 ;

Contextual Kohonen SOM with Orthogonal Weight Estimator Principle

Pican N. - p.667 ;


Robotics, Adaptive Autonomous Agents, and Control

Invited Plenay Talk S16 (10.10. - 14h15)

Self-Organizing Maps for Robot Control

Ritter H. - p.675 ;

S5, Invited Special Session: Adaptive Autonomous Agents I (8.10; 10h30-12.15)

Oral Presentations

Cognition is Not Computation: Evolution is Not Optimisation

Harvey I. - p.685 ;

Information Theoretic Implications of Embodiment for Neural Network Learning

Scheier C., Pfeifer R. - p.691 ;

Visual Attention and Learning of a Cognitive Robot

Tani J. - p.697 ;

Feature Binding Through Temporally Correlated Neural Activity in a Robot Model of Visual Perception

Egner S., Scheier C. - p.703 ;

Poster Spotlights

Modeling Obstacle Avoidance Behavior of Flies Using an Adaptive Autonomous Agent

Huber S.A., Buelthoff H.H. - p.709 ;

Minimalistic Approach to 3D Obstacle Avoidance Behavior from Simulated Evolution

Neumann T.R., Huber S.A., and Buelthoff H.H. - p.715 ;

Synthesis of Developmental and Evolutionary Modeling of Adaptive Autonomous Agents

Vaario J., Shimohara K. - p.721 ;

Hebbian Multilayer Network in a Wheelchair Robot

Buehlmeier A., Steiner P., Rossmann M., Goser K., and Manteuffel G. - p.727 ;

S10, Invited Special Session: Adaptive Autonomous Agents II (8.10; 16h00 - 17h45)

Oral Presentations

Neural Networks in an Artificial Life Perspective

Nolfi S., Parisi D. - p.733 ;

Incremental Acquisition of Local Networks for the Control of Autonomous Robots

Millan J. - p.739 ;

Robot-Animal Interaction

Lund H.H. - p.745 ;

The View-Graph Approach to Visual Navigation and Spatial Memory

Mallot H.A., Franz M., Schoelkopf B., and Buelthoff H.H. - p.751 ;

Poster Spotlights

Place Sequence Learning for Navigation

Trullier O., Meyer J.A. - p.757 ;

Learning to Communicate Through Imitation in Autonomous Robots

Billard A., Hayes G. - p.763 ;

On Learning Soccer Strategies

Salustowicz R., Wiering M., and Schmidhuber J. - p.769 ;

A Model of Logic Like Inference by Memory Model PATON

Mizutani K., Omori T. - p.775 ;

S18: Robotics (9.10; 15h00 - 16h45)

Oral Presentations

Force Feedback Control of an Assembly Robot by Neural Networks

Saadia N., Amirat Y., Pontnau J., and Ramdane-Cherif A. - p.781 ;

Neural Force Control (NFC) for Complex Manipulator Tasks

Dapper M., Maass R., Zahn V., and Eckmiller R. - p.787 ;

A Hybrid Path Planning System Combining the A*-Method and RBF-Networks*

Frontzek T., Goerke N., and Eckmiller R. - p.793 ;

An ASSOM Neural Network to Represent Actions Performed by an Autonomous Agent

Chella A., Gaglio S., Mulia V., and Sajeva G. - p.799 ;

Poster Spotlights

The Application of Radial Basis Function Networks with Implicit Continuity Constraints

Salomon R. - p.805 ;

Autonomous Vehicle Guidance Using Analog VLSI Neuromorphic Sensors

Indiveri G., Verschure P. - p.811 ;

Neural Network Visual Tracking System

Ortmann V., Eckmiller R. - p.817 ;

Pole-Balancing with Different Evolved Neurocontrollers

Pasemann F. - p.823 ;

Calibration of Parallel Robots by Evolutionary Algorithm

Kokcharov I. - p.831 ;

On Use of ANNs to Model and to Control Robot Manipulators

Duleba I., Muszynski R. - p.837 ;

S28: Identification and Control (10.10; 15h10-16h50)

Oral Presentations

Identification of the Electric Arc of a Furnace

Ledoux C., Bonnard F. - p.843 ;

On Using MLPs for Step Size Control in Echo Cancellation for Hands- Free Telephone Sets

Breining C., Alt G. - p.849 ;

Neurocontrol of Nonlinear Dynamic Systems Subject to Unmeasured Disturbance Inputs

Habtom R., Litz L. - p.855 ;

Multiple Multivariate Regression and Global Optimization in a Large Scale Thermodynamical Application

Zaragoza H., Gallinari P., Curtelin R., and Leglaye F. - p.861 ;

A Neural Network for Parameter Estimation of a DC Motor for Feed-Drives

Desforges X., Habbadi A. - p.867 ;


Speech, Vision, and Pattern Recognition

Invited Plenay Talk S26 (10.10 - 13h30)

State-of-the-Art and Recent Progress in Hybrid HMM/ANN Speech Recognition

Bourlard H. - p.875}

Invited Plenay Talk S16 (9.10. - 14h00)

Perceptual Grouping and Attention During Cortical Form and Motion Processing

Grossberg S. - p.885 ;

S25: Vision (10.10; 10h30-12.15)

Oral Presentations

Development of Shape Primitives from Images of Composite Objects Represented by Complex Cells

Shams L., von der Malsburg C. - p.895 ;

Corner Detection in Color Images by Multiscale Combination of End-Stopped Cortical Cells

Wuertz R.P., Lourens T. - p.901 ;

Constructing the Cyclopean View

Henkel R.D. - p.907 ;

SAIM: A Model of Visual Attention and Neglect

Heinke D., Humphreys G.W. - p.913 ;

S13: Pattern Recognition (9.10; 10h30-12.15)

Oral Presentations

Object Selection with Dynamic Neural Maps

Hamker F.H., Gross H.M. - p.919 ;

A Pre-Processing Technique Based on the Wavelet Transform for Linear Autoassociators with Applications to Face Recognition

Yang F., Paindavoine M., and Abdi H. - p.925 ;

Recognition and Segmentation of Components of a Face by a Multi- Resolution Neural Network

Fukushima K., Hashimoto H. - p.931 ;

Sensor Fusion for Mine Detection with the RNN

Gelenbe E., Kocak T., and Collins L. - p.937 ;

Poster Spotlights

Image Segmentation for 3D Object Recognition Using Bidirectional Networks

Fujita T., Ando H. - p.943 ;

A Feature Map Approach to Pose Estimation Based on Quaternions

Winkler S., Wunsch P., and Hirzinger G. - p.949 ;

Facial Feature Detection Using Neural Networks

Varchmin A.C., Rae R., and Ritter H. - p.955 ;

Random Neural Network Recognition of Shaped Objects in Strong Clutter

Bakircioglu H., Gelenbe E., and Carin L. - p.961 ;

AdaBoosting Neural Networks: Application to on-line Character Recognition

Schwenk H., Bengio Y. - p.967 ;

Cursive Script Recognition with Time Delay Neural Networks Using Learning Hints

Marti U.-V., Kaufmann G., and Bunke H. - p.973 ;


Prediction, Forecasting, and Monitoring

S22, Invited Special Session: Prediction (10.10; 10h30-12.15)

Oral Presentations

A Powerful Tool for Fitting and Forecasting Deterministic and Stochastic Processes: the Kohonen Classification

de Bodt E., Gr'egoire P., and Cottrell M. - p.981 ;

Neural Model Selection: How to Determine the Fittest Criterion?

Mangeas M. - p.987}

Long Term Forecasting by Combining Kohonen Algorithm and Standard Prevision

Cottrell, M., Girard B., and Rousset P. - p.993 ;

Predicting Time Series with Support Vector Machines

Mueller K.R., Smola A.J., Ratsch G., Schoelkopf B., Kohlmorgen J., and Vapnik V.N. - p.999 ;

An Extended Neuron Model for Efficient Time-Series Generation and Prediction

Burg T., Tschichold-Guerman N. - p.1005 ;

S4: Forecasting (8.10; 10h30-12.15)

Oral Presentations

Different Model Types for Short-Term Forecasting of Characteristic Load Points

Monteyne M., Salom'e T., de Viron F., Renders J.-M., Doulliez P., Dongier F., and Claus J. - p.1011 ;

Assessing Error Bars in Distribution Load Curve Estimation

Fidalgo J.N., Matos M.A., and Ponce de Leao M.T. - p.1017 ;

Building High Performant Classifiers by Integrating Bayesian Learning, Mutual Information and Committee Techniques - A Case Study in Time Series Prediction

Ragg T., Gutjahr S. - p.1023 ;

A Probability Estimation Based Criteria for Model Evaluation

Czernichow T., Munoz A. - p.1029 ;

Poster Spotlights

Short-term Load Forecasting Based on Correlation Dimension Estimation and Neural Nets

Camastra F., Colla A.M. - p.1035 ;

Predictive Neural Models in Noisy Environment

Lenez T., Dorizzi B. - p.1041 ;

A Neural-FIR Predictor: Minimum Size Estimation Based on Nonlinearity Analysis of Input Sequence

Khalaf A.A.M., Nakayama K,, and Hara K. - p.1047 ;

Modelling Conditional Probabilities with Committees of RVFL Networks

Husmeier D., Taylor J.G. - p.1053 ;

S8: Monitoring (8.10; 16h00 - 17h45)

Oral Presentations

Classifying the Wear of Turning Tools with Neural Networks

Sick B. - p.1059 ;

Detection of Mobile Phone Fraud Using Supervised Neural Networks: A First Prototype

Moreau Y., Verrelst H., and Vandewalle J. - p.1065 ;

Wiener type SOM- and MLP-classifiers for Recognition of Dynamic Modes

Visala A., Pitkanen H., and Halme A. - p.1071 ;

Analysis of Wake/Sleep EEG with Competing Experts

Kohlmorgen J., Mueller K.R., Rittweger J., and Pawelzik K. - p.1077 ;

Poster Spotlights

Nonlinear Modelling of the Daily Heart Rhythm

Silipo R., Deco G., Vergassola R., Schnittenkopf C., and Gremigni C. - p.1083 ;

Linear and Nonlinear Combinations of Connectionist Models for Local Diagnosis in Real-Time Telephone Network Traffic Management

Bennani Y., Bossaert F., and Didelet E. - p.1089 ;

Neural Network Adaptive Modeling of Battery Discharge Behavior

G'erard O., Patillon J.-N., and d'Alch'e-Buc F. - p.1095 ;

Neural Combustion Control

Mueller R. - p.1101 ;

A Neural Network Based Fault Detector for Power Distribution Systems

Assef Y., Bastard P., and Meunier M. - p.1107 ;

Visualization and Analysis of Voltage Stability Using Self-Organizing Neural Networks

Handschin E., Kuhlmann D., and Rehtanz C. - p.1113 ;

Classification of Meteorological Patterns

Ambuehl J., Cattani D., and Eckert P. - p.1119 ;

Mapping of Soil Contamination by Using Artificial Neural Networks and Multivariate Geostatistics

Kanevski M., Demyanov V., and Maignan M. - p.1125 ;


Implementations

Invited Plenay Talk S11 (9.10. - 9h15)

Pseudo-Resistive Networks and their Applications to Analog Collective Computation

Vittoz E. - p.1133 ;

Invited Plenay Talk S11 (9.10. - 8h30)

Implementation of CNN Computing Technology

Roska T. - p.1151 ;

S15: Analog VLSI (9.10; 10h30-12.15)

Oral Presentations

Implementation of a Masking Network for Speech Perception

Chiueh T.D., Bu L. - p.1157 ;

Real-Time Analog VLSI Sensors for 2-D Direction of Motion

Deutschmann R.A., Higgins C.M., and Koch C. - p.1163 ;

An Improved Multiplexed Resistive Network for Analog Image Preprocessing

Yi C.H., Schlabbach R., Kroth H., and Klar H. - p.1169 ;

An Analog VLSI Computational Engine for Early Vision Tasks

Bisio G.M., Bo G.M., Confalone M., Raffo L., Sabatini S.P., and Zizola M.P. - p.1175 ;

Poster Spotlights

Spatio-Temporal Filter Adjustment from Evaluative Feedback for a Retina Implant

Becker M., Eckmiller R. - p.1181 ;

Simulation of Spiking Neural Networks on Different Hardware Platforms

Jahnke A., Schoenauer T., Roth U., Mohraz K., and Klar H. - p.1187 ;

Adaptive On-line Learning Algorithm for Robust Estimation of Parameters of Noisy Sinusoidal Signals

Lobos T., Cichocki A., Kostyla P., and Waclawek Z. - p.1193 ;

Analog Sequential Architecture for Neuro-Fuzzy Models VLSI Implementation

Moreno J.M., Madrenas J., Alarcon E., and Cabestany J. - p.1199 ;

A Mixed-Signal VLSI Circuit for Skeletonization by Grassfire Transformation

Olah M., Masa P., and Lorincz A. - p.1205 ;

S20: Digital Implementations (9.10; 15h00 - 16h45)

Oral Presentations

Analysis and Improvement of Neural Network Robustness for On-Board Satellite Image Processing

Muller J.-D., Cheynet P., and Velazco R. - p.1211 ;

On-Line Hebbian Learning for Spiking Neurons: Architecture of the Weight-Unit of NESPINN

Roth U., Jahnke A., and Klar H. - p.1217 ;

Measurement of Finite-Precision Effects in Handwriting- and Speech- Recognition Algorithms

Sackinger E. - p.1223 ;

A Hardware Implementation of Hierarchical Neural Networks for Real-Time Quality Control Systems in Industrial Applications

Baratta D., Bo G.M., Caviglia D.D., Valle M., Canepa G., Parenti R., and Penno C. - p.1229 ;

Poster Spotlights

The SAND Neurochip and its Embedding in the MiND System

Fischer T., Eppler W., Gemmeke H., Kock G., and Becher T. - p.1235 ;

Short- and Long-Term Dynamics in a Stochastic Pulse Stream Neuron Implementation in FPGA

Rossmann M., Buehlmeier A., Manteuffel G., and Goser K. - p.1241 ;

FPGA Implementation of a Network of Neuronlike Adaptive Elements

P'erez-Uribe A., Sanchez E. - p.1247 ;

Handwritten Digit Recognition with Binary Optical Perceptron

Saxena I., Moerland P., Fiesler E., and Pourzand A. - p.1253 ;

Mapping of Radial Basis Function Networks to Partial Tree Shape Parallel Neurocomputer

Kolinummi P., Hamalainen T., and Saarinen J. - p.1259 ;

Attractor dynamics in an electronic neural network

Del Giudice P., Fusi S. - p.1265 ;