ESANN 1997: Bruges, Belgium

Models I

• Edmondo Trentin, Diego Giuliani: Speaker normalization with a mixture of recurrent networks.
• Yvon Autret, Andre Thepaut: Neural network cooperation for handwritten digit recognition: a comparison of four methods.
• Fatiha Anouar, Fouad Badran, Sylvie Thiria: Probabilistic self organized map - application to classification.
• Leonardo Maria Reyneri, Mirko Sgarbi: Performance of weighted radial basis function classifiers.
• Igor Grabec: Equivalence of a radial basis function NN and a perceptron.

Biological modelling and vision

• Tom W. Scutt, Barbara Webb: Real neurons in real networks.
• M. Mougeot: Synchronization and oscillations in the visual cortex: a stochastic model using a spike memory term.
• Antonio B. Torralba, Jeanny Hérault: From retinal circuits to motion processing: a neuromorphic approach to velocity estimation.
• Gotz Meierfrankenfeld, Klaus Kopecz: Size invariance by dynamic scaling in neural vision systems.
• Norbert Krüger, Gabriele Peters: Object Recognition with Banana Wavelets. 61-66

Invited session: Object and scene recognition: experimental results and models

• Michael D'Zmura: Neural network for color contrast gain control.
• Rolf P. Würtz: Neuronal theories and technical systems for face recognition.
• Simon J. Thorpe: How can the human visual system process a natural scene in under 150ms? Experiments and neural network models.
• Philippe G. Schyns: Aspects of psychological computations in scene recognition.
• Jeanny Hérault: Scene classification by an artificial neural network.

Statistics and rule extraction

• Michiel C. van Wezel, Joost N. Kok, Walter A. Kosters: Two neural network methods for multidimensional scaling.
• Ulrich Anders, Olaf Korn: Sequential hypotheses tests for modelling neural networks.
• Wlodzislaw Duch, Rafal Adamczak, Krzysztof Grabczewski, Masumi Ishikawa, Hiroki Ueda: Extraction of crisp logical rules using constrained backpropagation networks.
• Frédéric Alexandre, Jean-Francois Remm: Knowledge extraction from neural networks for signal interpretation.
• Peter Sykacek: Equivalent error bars for neural network classifiers trained by Bayesian inference.

Forecasting and chaos

• Denis Bonnet, Véronique Perrault, Alain Grumbach: d-NARMA neural networks: a connectionist extension of ARARMA models.
• Morgan Mangeas, Marie Cottrell, Jian-Feng Yao: New criterion of identification in the multilayered perceptron modelling.
• Tomas Hrycej: Error measure for identifying chaotic attractors.
• Joan Ferré-Giné, Robert Rallo, Alex Arenas, Francesc Giralt: A fuzzy Artmap neural system for the prediction of turbulent velocity fields.

• Arnaud Buhot, Juan Manuel Torres Moreno, Mirta B. Gordon: Numerical simulations of an optimal algorithm for supervised learning.
• Chulan Kwon, Jong-Hoon Oh: Exact asymptotic estimates of the storage capacities of the committee machines with overlapping and non-overlapping receptive fields.
• Nicolas Brunel, Jean-Pierre Nadal: Optimal tuning curves for neurons spiking as a Poisson process.
• Ole Winther, Sara A. Solla: Bayesian online learning in the perceptron.
• Bart Van Rompaey: Precursor networks for training the binary perceptron.
• Mauro Copelli: Noise robustness in the perceptron.

Self-organizing maps

• Heikki Hyötyniemi: State-space modeling using self-organizing maps.
• Avec M. Benaïm, Jean-Claude Fort, Gilles Pagès: Almost sure convergence of the one-dimensional Kohonen algorithm.
• Ana Isabel González, Manuel Graña, Alicia D'Anjou, F. Xabier Albizuri, Marie Cottrell: Self organizing map for adaptive non-stationary clustering: some experimental results on color quantization of image sequences.
• J. Michael Herrmann, Hans-Ulrich Bauer, Thomas Villmann: Measuring topology preservation in maps of real-world data.
• Eric de Bodt, Michel Verleysen, Marie Cottrell: Kohonen maps versus vector quantization for data analysis.

Learning I

• Mohamed Tajine, David A. Elizondo, Emile Fiesler, Jerzy J. Korczak: The class of linear separability method.
• Michael St Aubyn: Connectionist rule processing using recursive auto-associative memory.
• Georges Vaucher: An algebra for recognition of spatio-temporal forms.
• Martin A. Riedmiller: Application of a self-learning controller with continuous control signals based on the DOE-approach.

Invited session: Source separation and Independent Component Analysis

• Christian Jutten: From source separation to ICA: an introduction to the special session.
• Seungjin Choi, Ruey-Wen Liu: A learning algorithm for the blind separation of non-zero skewness source signals with no spurious equilibria.
• Petteri Pajunen: A competitive learning algorithm for separating binary sources.
• Zied Malouche, Odile Macchi: A linear adaptive neural network for extraction of independent components.
• X.-R. Cao, J. Zhu, J. Si: Blind equalization with a linear feedforward neural network.
• Nabil Charkani, Yannick Deville: Optimization of the asymptotic performance of time-domain convolutive source separation algorithms.
• Anisse Taleb, Christian Jutten: Nonlinear source separation: the post-nonlinear mixtures.
• Jean-Pierre Nadal, Néstor Parga: I.C.A.: conditions on cumulants and information theoretic approach.
• Lei Xu, Chi Chiu Cheung, Jiong Ruan, Shun-ichi Amari: Nonlinearity and separation capability: further justification for the ICA algorithm with mixture of densities.
• Mark Girolami, Colin Fyfe: Independence is far from normal.

Learning II

• Yves Moreau, Joos Vandewalle: Composition methods for the integration of dynamical neural networks.
• Youichi Kobuchi: Order between logic networks and stable neural networks.
• M. Wexler: Inductive learning in animat-based neural networks.
• Steffen Gutjahr, Christian Nautze: Extended Bayesian learning.

Models II

• Jean-Philippe Draye, Davor Pavisic, Guy Cheron, Gaetan Libert: Evidence of efficiency of recurrent neural networks with ARMA-like units.
• Paul I. Miller: Recurrent neural networks and motor programs.
• A. Korgul: Time delay neural network for target-intercept problem solving.
• Yong Fang, Tommy W. S. Chow: Neural network adative wavelets for function approximation.