ESANN1997

5th European Symposium on Artificial Neural Networks
Bruges, Belgium, April 16-17-18

[Electronic proceedings home page] [Electronic proceedings author index]

ESANN1997
Content of the proceedings

WARNING: you need Adobe Acrobat reader 7.0 or more to view the PDF files below



Models I


ES1997-20

Speaker normalization with a mixture of recurrent networks

E. Trentin, D. Giuliani

Abstract
not yet available

Scanned document [PDF]

ES1997-55

Neural network cooperation for handwritten digit recognition: a comparison of four methods

Y. Autret, A. Thepaut

Abstract
In this paper we focus on "off-line" recognition with unknown scriptor. We only consider isolated digits. We present an approach whose aim is simplicity and performance. Two simple neural solutions are first presented. Their main characteristic is non neural pretreatment reduced as much as possible. A simple method for integration is then proposed. The method has been evaluated on a database from french postal services (SRTP). This data base contains 12000 digits and is kept secret.

Manuscript from author [PDF]

ES1997-56

Probabilistic self organized map - application to classification

F. Anouar, F. Badran, S. Thiria

Abstract
not yet available

Scanned document [PDF]

ES1997-35

Performance of weighted radial basis function classifiers

L.M. Reyneri, M. Sgarbi

Abstract
This paper describes Weighted Radial Basis Functions, a neuro-fuzzy unification algorithm which mixes Perceptrons and Radial Basis Functions. The algorithm has been tested as a pattern classifier in practical applications. Its performance are compared against those of other neural classifiers. The proposed algorithm has performance comparable or better than other neural algorithms, although it can be trained much faster. It can also act as a neuro-fuzzy unification algorithm.

Scanned document [PDF]

ES1997-42

Equivalence of a radial basis function NN and a perceptron

I. Grabec

Abstract
not yet available

Scanned document [PDF]

[Back to Top]


Biological modelling and vision


ES1997-23

Real neurons in real networks

T. Scutt, B. Webb

Abstract
not yet available

Scanned document [PDF]

ES1997-65

Synchronization and oscillations in the visual cortex: a stochastic model using a spike memory term

M. Mougeot

Abstract
not yet available

Scanned document [PDF]

ES1997-40

From retinal circuits to motion processing: a neuromorphic approach to velocity estimation

A. Torralba, J. Hérault

Abstract
not yet available

Scanned document [PDF]

ES1997-51

Size invariance by dynamic scaling in neural vision systems

G. Meierfrankenfeld, K. Kopecz

Abstract
not yet available

Scanned document [PDF]

ES1997-60

Object recognition with banana wavelets

N. Krüger, G. Peters

Abstract
not yet available

Scanned document [PDF]

[Back to Top]


Invites session: Object and scene recognition - experimental results and models


ES1997-501

Neural network for color contrast gain control

M. D'Zmura

Abstract
not yet available

Scanned document [PDF]

ES1997-502

Neuronal theories and technical systems for face recognition

R.P. Würtz

Abstract
not yet available

Scanned document [PDF]

ES1997-503

How can the visual system process a natural scene in under 150ms? On the role of asynchronous spike propagation

S. Thorpe, J. Gautrais

Abstract
not yet available

Scanned document [PDF]

ES1997-504

Aspects of psychological computation in scene and face recognition

P. Schyns

Abstract
not yet available

Scanned document [PDF]

ES1997-505

Scene categorisation by curvilinear component analysis of low frequency spectra

J. Hérault, A. Olivia, A. Guérin-Dugué

Abstract
not yet available

Scanned document [PDF]

[Back to Top]


Statistics and rule extraction


ES1997-43

Two neural network methods for multidimensional scaling

M. C. van Wezel, J. N. Kok, W. A. Kosters

Abstract
not yet available

Scanned document [PDF]

ES1997-3

Sequential hypotheses tests for modelling neural networks

U. Anders, O. Korn

Abstract
not yet available

Scanned document [PDF]

ES1997-68

Extraction of crisp logical rules using constrained backpropagation networks

W. Duch, R. Adamczak, K. Grabczewski, M. Ishikawa, H. Ueda

Abstract
not yet available

Scanned document [PDF]

ES1997-72

Knowledge extraction from neural networks for signal interpretation

F. Alexandre, J.-F. Remm

Abstract
not yet available

Scanned document [PDF]

ES1997-17

Equivalent error bars for neural network classifiers trained by Bayesian inference

P. Sykacek

Abstract
not yet available

Scanned document [PDF]

[Back to Top]


Forecasting and chaos


ES1997-53

d-NARMA neural networks: a connectionist extension of ARARMA models

D. Bonnet, V. Perrault, A. Grumbach

Abstract
not yet available

Scanned document [PDF]

ES1997-80

New criterion of identification in the multilayered perceptron modelling

M. Mangeas, M. Cottrell, J.-F. Yao

Abstract
not yet available

Scanned document [PDF]

ES1997-2

Error measure for identifying chaotic attractors

T. Hrycej

Abstract
not yet available

Scanned document [PDF]

ES1997-47

A fuzzy Artmap neural system for the prediction of turbulent velocity fields

J. Ferre-Gine, R. Rallo, A. Arenas, F. Giralt

Abstract
not yet available

Scanned document [PDF]

[Back to Top]


Invited session: Theory of neural networks with statistical mechanics approaches


ES1997-506

Numerical simulations of an optimal algorithm for supervised learning

A. Buhot, J.-M. Torres Moreno, M. B. Gordon

Abstract
not yet available

Scanned document [PDF]

ES1997-507

Exact asymptotic estimates of the storage capacities of the committee machines with overlapping and non-overlapping receptive fields

C. Kwon, J.-H. Oh

Abstract
not yet available

Scanned document [PDF]

ES1997-508

Optimal tuning curves for neurons spiking as a Poisson process

N. Brunel, J.P. Nadal

Abstract
not yet available

Scanned document [PDF]

ES1997-509

Bayesian online learning in the perceptron

O. Winther, S. A. Solla

Abstract
not yet available

Scanned document [PDF]

ES1997-510

Precursor networks for training the binary perceptron

B. Van Rompaey

Abstract
not yet available

Scanned document [PDF]

ES1997-511

Noise robustness in the perceptron

M. Copelli

Abstract
not yet available

Scanned document [PDF]

[Back to Top]


Self-organizing maps


ES1997-36

State-space modeling using self-organizing maps

H. Hyötyniemi

Abstract
Dynamic processes can be modeled using self-organizing maps, for example, by using the states of the system as input feature vectors to the self-organization algorithm. The neural net converges according to the distribution of the state variables, and, in principle, this map can be seen as a compressed representation of the state space. However, the distance metric which the Kohonen type adaptation algorithms are based on is not justified when measuring distances between process states. In this paper, the process to be modeled is modified so that the `static´ norm between states is applicable also when measuring distances between trajectories.

Manuscript from author [PDF]

ES1997-41

Almost sure convergence of the one-dimensional Kohonen algorithm

M. Benaïm, J.-C. Fort, G. Pagès

Abstract
not yet available

Scanned document [PDF]

ES1997-54

Self organizing map for adaptive non-stationary clustering: some experimental results on color quantization of image sequences

A.I. Gonzales, M. Grana, A. D'Anjou, F.X. Albizuri, M. Cottrell

Abstract
not yet available

Scanned document [PDF]

ES1997-75

Measuring topology preservation in maps of real-world data

M. Herrmann, H.-U. Bauer, T. Villmann

Abstract
not yet available

Scanned document [PDF]

ES1997-77

Kohonen maps versus vector quantization for data analysis

E. de Bodt, M. Verleysen, M. Cottrell

Abstract
not yet available

Manuscript from author [PDF]

[Back to Top]


Learning I


ES1997-28

The class of linear separability method

M. Tajine, D. Elizondo, E. Fiesler, J. Korczak

Abstract
not yet available

Scanned document [PDF]

ES1997-57

Connectionist rule processing using recursive auto-associative memory

M. St Aubyn, N. Davey

Abstract
not yet available

Scanned document [PDF]

ES1997-62

An algebra for recognition of spatio-temporal forms

G. Vaucher

Abstract
not yet available

Scanned document [PDF]

ES1997-67

Application of a self-learning controller with continuous control signals based on the DOE-approach

M. Riedmiller

Abstract
not yet available

Scanned document [PDF]

[Back to Top]


Invited session: Source separation and Independent Component Analysis


ES1997-512

From source separation to Independent Component Analysis: an introduction to the special session

C. Jutten

Abstract
not yet available

Scanned document [PDF]

ES1997-513

A learning algorithm for the blind separation of non-zero skewness source signals with no spurious equilibria

S. Choi, R.-W. Liu

Abstract
not yet available

Scanned document [PDF]

ES1997-514

A competitive learning algorithm for separating binary sources

P. Pajunen

Abstract
not yet available

Scanned document [PDF]

ES1997-515

A linear adaptive neural network for extraction of independent components

Z. Malouche, O. Macchi

Abstract
not yet available

Scanned document [PDF]

ES1997-516

Blind equalization with a linear feedforward neural network

X.-R. Cao, J. Zhu, J. Si

Abstract
not yet available

Scanned document [PDF]

ES1997-517

Optimization of the asymptotic performance of time-domain convolutive source separation algorithms

N. Charkani, Y. Deville

Abstract
not yet available

Scanned document [PDF]

ES1997-518

Nonlinear source separation: the post-nonlinear mixtures

A. Taleb, C. Jutten

Abstract
not yet available

Scanned document [PDF]

ES1997-519

I.C.A.: conditions on cumulants and information theoretic approach

J.-P. Nadal, N. Parga

Abstract
not yet available

Scanned document [PDF]

ES1997-520

Nonlinearity and separation capability: further justification for the ICA algorithm with a learned mixture of parametric densities

L. Xu, C.C. Cheung, J. Ruan, S.-I. Amari

Abstract
not yet available

Scanned document [PDF]

ES1997-521

Independence is far from normal

M. Girolami, C. Fyfe

Abstract
not yet available

Scanned document [PDF]

[Back to Top]


Learning II


ES1997-70

Composition methods for the integration of dynamical neural networks

Y. Moreau, J. Vandewalle

Abstract
not yet available

Scanned document [PDF]

ES1997-9

Order between logic networks and stable neural networks

Y. Kobuchi

Abstract
not yet available

Scanned document [PDF]

ES1997-39

Inductive learning in animat-based neural networks

M. Wexler

Abstract
not yet available

Scanned document [PDF]

ES1997-16

Extended Bayesian learning

S. Gutjahr, C. Nautze

Abstract
not yet available

Scanned document [PDF]

[Back to Top]


Models II


ES1997-8

Evidence of efficiency of recurrent neural networks with ARMA-like units

J.P. Draye, D. Pavisic, G. Cheron, G. Libert

Abstract
not yet available

Scanned document [PDF]

ES1997-66

Recurrent neural networks and motor programs

P. I. Miller

Abstract
not yet available

Scanned document [PDF]

ES1997-15

Time delay neural network for target-intercept problem solving

A. Korgul

Abstract
not yet available

Scanned document [PDF]

ES1997-21

Neural network adative wavelets for function approximation

F. Yong, T.W.S. Chow

Abstract
not yet available

Scanned document [PDF]

[Back to Top]