ESANN 1995 programme

Wednesday 19th April 1995

• 8H30 Registration
• 9H00 Opening session

  Session 1: Self-organisation
  Chairman: F. Blayo (Univ. Paris I, France)

• 9H10 "Self-organisation, metastable states and the ODE method in the Kohonen neural network"
  J.A. Flanagan, M. Hasler
  E.P.F. Lausanne (Switzerland)
• 9H30 "About the Kohonen algorithm: strong or weak self-organization?"
  J.-C. Fort*, G. Pages**
  *Univ. Nancy I & Univ. Paris I (France), **Univ. Paris 6 & Univ. Paris 12 (France)
• 9H50 "Topological interpolation in SOM by affine transformations"
  J. Goppert, W. Rosenstiel
  Univ. Tuebingen (Germany)
• 10H10 "Dynamic Neural Clustering"
  K. Moscinska
  Silesian Tech. Univ. (Poland)
• 10H30 "Multiple correspondence analysis of a crosstabulations matrix using the Kohonen algorithm"
  S. Ibbou, M. Cottrell
  Univ. Paris I (France)
• 10H50 Coffee break

  Session 2: Models 1
  Chairman: J. Stonham (Brunel Univ., United Kingdom)

• 11H10 "Identification of the human arm kinetics using dynamic recurrent neural networks"
  J.-P. Draye*, G. Cheron**, M. Bourgeois**, D. Pavisic*, G. Libert*
  *Fac. Polytech. de Mons (Belgium), **Univ. Brussels (Belgium)
• 11H30 "Simplified cascade-correlation learning"
  M. Lehtokangas, J. Saarinen, K. Kaski
  Tampere Univ. of Technology (Finland)
• 11H50 "Active noise control with dynamic recurrent neural networks"
  D. Pavisic, L. Blondel, J.-P. Draye, G. Libert, P. Chapelle
  Fac. Polytech. de Mons (Belgium)
• 12H10 "Cascade learning for FIR-TDNNs"
  M. Diepenhorst, J.A.G. Nijhuis, L. Spaanenburg
  Rijksuniv. Groningen (The Netherlands)
• 12H30 Lunch
• 14H00 Invited paper:
  D. Stork (Ricoh California Research Center), A. Sperduti (Univ. di Pisa)
  "Recent developments in transformation-invariant pattern classification"

  Session 3: Signal processing and chaos
  Chairman: M. Hasler (E.P.F. Lausanne, Switzerland)

• 14H45 "Adaptive signal processing with unidirectional Hebbian adaptation laws"
  J. Dehaene, J. Vandewalle
  Kat. Univ. Leuven (Belgium)
• 15H05 "MAP decomposition of a mixture of AR signal using multilayer perceptrons"
  C. Couvreur
  Fac. Polytech. de Mons (Belgium)
• 15H25 "XOR and backpropagation learning: in and out of the chaos?"
  K. Bertels*, L. Neuberg*, S. Vassiliadis**, G. Pechanek***
  *Fac. Univ. N.-D. de la Paix (Belgium), **T.U. Delft (The Netherlands), ***IBM Microelectronics Div. (USA)
• 15H45 "Analog Brownian weight movement for learning of artificial neural networks"
  M.R. Belli, M. Conti, C. Turchetti
  Univ. of Ancona (Italy)
• 16H05 Coffee break

  Session 4: Biological models
  Chairman: H.P. Mallot (Max-Planck Institut, Germany)

• 16H30 "Spatial summation in simple cells: computational and experimental results"
  F. Worgotter*, E. Nelle*, B. Li**, L. Wang**, Y.-C. Diao**
  *Ruhr Univ. Bochum (Germany), **Academia Sinica (China)
• 16H50 "Activity-dependent neurite outgrowth in a simple network model including excitation and inhibition"
  C. van Oss, A. van Ooyen
  Neth. Inst. for Brain Research (The Netherlands)
• 17H10 "Predicting spike train responses of neuron models"
  S. Joeken, H. Schwegler
  Univ. of Bremen (Germany)
• 17H30 "A distribution-based model of the dynamics of neural networks in the cerebral cortex"
  A. Terao*, M. Akamatsu*, J. Seal**
  *Nat. Inst. of Bioscience and Human Technology (Japan), **CNRS Marseilles (France)
• 17H50 "Some new results on the coding of pheromone intensity in an olfactory sensory neuron"
  A. Vermeulen*,**, J.-P. Rospars*, P. Lansky***,*, H.C. Tuckwell****,*
  *INRA (France), **I.N.P. Grenoble (France), ***Acad. of Sciences (Czech Republic), ****Australian Nat. Univ. (Australia)

Thursday 20th April 1995

Session 5: Special session on the Elena-Nerves2 ESPRIT Basic Research project
Chairman: M. Cottrell (Univ. Paris I, France)

• 9H00 Invited paper:
  P. Comon (Thomson-Sintra, France)
  "Supervised classification: a probabilistic approach"
• 9H30 Invited paper:
  C. Jutten, O. Fambon (Inst. Nat. Pol. Grenoble, France)
  "Pruning methods: a review"
• 10H00 "A deterministic method for establishing the initial conditions in the RCE algorithm"
  J.M. Moreno, F.X. Vazquez, F. Castillo, J. Madrenas,
  J. Cabestany Univ. Politecnica Catalunya (Spain)
• 10H20 "Pruning kernel density estimators"
  O. Fambon, C. Jutten
  Inst. Nat. Pol. Grenoble (France)
• 10H40 "Suboptimal Bayesian classification by vector quantization with small clusters"
  J.L. Voz, M. Verleysen, P. Thissen, J.D. Legat
  Univ. Cat. Louvain (Belgium)
• 11H00 Coffee break

  Session 6: Theory of learning systems
  Chairman: C. Touzet (IUSPIM Marseilles, France)

• 11H20 "Knowledge and generalisation in simple learning systems"
  D. Barber, D. Saad
  University of Edinburgh (United Kingdom)
• 11H40 "Control of complexity in learning with perturbed inputs"
  Y. Grandvalet*, S. Canu*, S. Boucheron**
  *Univ. Tech. de Compiegne (France), **Univ. Paris-Sud (France)
• 12H00 "An episodic knowledge base for object understanding"
  U.-D. Braumann, H.-J. Boehme, H.-M. Gross
  Tech. Univ. Ilmenau (Germany)
• 12H20 "Neurosymbolic integration: unified versus hybrid approaches"
  M. Hilario*, Y. Lallement**, F. Alexandre**
  *Univ. Geneve (Switzerland), **INRIA (France)
• 12H40 Lunch

  Session 7: Biological vision
  Chairman: J. Herault (Inst. Nat Polyt. Grenoble, France)

• 14H00 "Improving object recognition by using a visual latency mechanism"
  R. Opara, F. Worgorter
  Ruhr Univ. Bochum (Germany)
• 14H20 "On the function of the retinal bipolar cell in early vision"
  S. Ohshima, T. Yagi, Y. Funahashi
  Nagoya Inst. of Technology (Japan)
• 14H40 "Sustained and transient amacrine cell circuits underlying the receptive fields of ganglion cells in the vertebrate retina"
  G. Maguire
  Univ. of Texas (USA)
• 15H00 "Latency-reduction in antagonistic visual channels as the result of corticofugal feedback"
  J. Kohn, F. Worgotter
  Ruhr Univ. Bochum (Germany)
• 15H20 Coffee break

  Session 8: Models 2
  Chairman: V. Kurkova (Academy of Sciences, Czech Republic)

• 15H40 "On threshold circuit depth"
  A. Albrecht
  BerCom GmbH (Germany)
• 16H00 "Minimum entropy queries for linear students learning nonlinear rules"
  P. Sollich
  Univ. of Edinburg (United Kingdom)
• 16H20 "An asymmetric associative memory model based on relaxation labeling processes"
  M. Pelillo, A.M. Fanelli
  Univ. di Bari (Italy)
• 16H40 "Invariant measure for an infinite neural network "
  T.S. Turova
  Kat. Univ. Leuven (Belgium)
• 17H00 "Growing adaptive neural networks with graph grammars"
  S.M. Lucas
  Univ. of Essex (United Kingdom)
• 17H20 "Constructing feed-forward neural networks for binary classification tasks"
  C. Campbell*, C. Perez Vincente**
  *Bristol Univ. (United Kingdom), **Univ. Barcelona (Spain)
• 20H00 Conference dinner

Friday 21th April 1995

Session 9: Classification and control
Chairman: M. Grana (UPV San Sebastian, Spain)

• 9H00 "Improvement of EEG classification with a subject-specific feature selection"
  M. Pregenzer, G. Pfurtscheller, C. Andrew
  Graz Univ. of Technology (Austria)
• 9H20 "Neural networks for invariant pattern recognition"
  J. Wood, J. Shawe-Taylor
  Univ. of London (United Kingdom)
• 9H40 "Derivation of a new criterion function based on an information measure for improving piecewise linear separation incremental algorithms"
  J. Cuguero, J. Madrenas, J.M. Moreno, J. Cabestany
  Univ. Politecnica Catalunya (Spain)
• 10H00 "Neural network based one-step ahead control and its stability"
  Y. Tan, A.R. Van Cauwenberghe
  Univ. of Gent (Belgium)
• 10H20 "NLq theory: unifications in the theory of neural networks, systems and control"
  J. Suykens, B. De Moor, J. Vandewalle
  Kat. Univ. Leuven (Belgium)
• 10H40 Coffee break
• 11H00 Invited paper:
  H.P. Mallot (Max-Planck-Institut, Germany)
  "Learning of cognitive maps from sequences of views"

  Session 10: Radial-basis functions
  Chairman: G. Pages (Univ. Paris VI, France)

• 11H45 "Trimming the inputs of RBF networks"
  C. Andrew*, M. Kubat**, G. Pfurtscheller*
  *Graz Univ. Tech. (Austria), **Johannes Kepler Univ. (Austria)
• 12H05 "Learning the appropriate representation paradigm by circular processing units"
  S. Ridella, S. Rovetta, R. Zunino
  Univ. of Genoa (Italy)
• 12H25 "Radial basis functions in the Fourier domain"
  M. Orr
  Univ. of Edinburgh (United Kingdom)
• 12H45 Lunch

  Session 11: Function approximation
  Chairman: J. Vandewalle (Kat. Univ. Leuven, Belgium)

• 14H00 "Function approximation by localized basis function neural network"
  M. Kokol, I. Grabec
  Univ. of Ljubljana (Slovenia)
• 14H20 "Functional approximation by perceptrons: a new approach"
  J.-G. Attali*, G. Pages**
  *Univ. Paris I (France), **Univ. Paris 6 & Univ. Paris 12 (France)
• 14H40 "Approximation of functions by Gaussian RBF networks with bouded number of hidden units"
  V. Kurkova
  Acad. of Sciences (Czech Republic)
• 15H00 "Neural network piecewise linear preprocessing for time-series prediction"
  T.W.S. Chow, C.T. Leung
  City Univ. (Hong-Kong)
• 15H20 "An upper estimate of the error of approximation of continuous multivariable functions by KBF networks" K. Hlavackova
  Acad. of Sciences (Czech Republic)
• 15H40 Coffee break

  Session 12: Multi-layer perceptrons
  Chairman: W. Duch (Nicholas Copernicus Univ., Poland)

• 16H00 "Multi-sigmoidal units and neural networks"
  J.A. Drakopoulos
  Stanford Univ. (USA)
• 16H20 "Performance analysis of a MLP weight initialization algorithm"
  M. Karouia, R. Lengelle, T. Denoeux
  Univ. Compiegne (France)
• 16H40 "Alternative output representation schemes affect learning and generalization of back-propagation ANNs; a decision support application"
  P.K. Psomas, G.D. Hilakos, C.F. Christoyannis, N.K. Uzunoglu
  Nat. Tech. Univ. Athens (Greece)
• 17H00 "A new training algorithm for feedforward neural networks"
  B.K. Verma, J.J. Mulawka
  Warsaw Univ. of Technology (Poland)
• 17H20 "An evolutive architecture coupled with optimal perceptron learning for classification"
  J.-M. Torres Moreno, P. Peretto, M. B. Gordon
  C.E.N. Grenoble (France)