[Electronic proceedings home page] | [Electronic proceedings author index] |
ESANN1998 Content of the proceedings |
WARNING: you need Adobe Acrobat reader 7.0 or more to view the PDF files below |
![]() |
I. Rojas, M. Anguita, E. Ros, H. Pomares, O. Valenzuela, A. Prieto
Abstract
not yet availableScanned document [PDF]
S. Wu, C. Van den Broeck
Abstract
not yet availableScanned document [PDF]
M. Sgarbi, V. Colla, L. Reyneri
Abstract
not yet availableScanned document [PDF]
A. Esposito, M. Marinaro, S. Scarpetta
Abstract
not yet availableScanned document [PDF]
C. Angulo, A. Catala
Abstract
not yet availableScanned document [PDF]
T. Takahashi
Abstract
not yet availableScanned document [PDF]
J. Feng, B. Tirozzi, D. Brown
Abstract
not yet availableScanned document [PDF]
C. Bernard, S. Mallat, J.-J. Slotine
Abstract
Abstract. We describe a new approach to real time learning of unknown functions based on an interpolating wavelet estimation. We choose a subfamily of a wavelet basis relying on nested hierarchical allocation and update in real time our estimate of the unknown function. Such an interpolation process can be used for real time applications like neural network adaptive control, where learning an unknown function very fast is critical.Manuscript from author [PDF]
Z. Yang, F. França
Abstract
not yet availableScanned document [PDF]
P. Werbos
Abstract
not yet availableScanned document [PDF]
J.-P. Draye, L. Blondel, G. Cheron
Abstract
not yet availableScanned document [PDF]
G. Bontempi, M. Birattari, H. Bersini
Abstract
This paper presents two local methods for the control of discrete-time unknown nonlinear dynamical systems, when only a limited amount of input-output data is available. The modeling procedure adopts lazy learning a query-based approach for local modeling inspired to memory-based approximators. In the first method the lazy technique returns the forward and inverse models of the system which are used to compute the control action to take. The second is an indirect method inspired to adaptive control where the self-tuning identification module is replaced by a lazy approximator. Simulation examples of control of nonlinear systems starting from observed data are given.Manuscript from author [PDF]
M. Baglietto, T. Parisini, R. Zoppoli
Abstract
not yet availableScanned document [PDF]
T. de Vries, L. Idema, W. Velthuis
Abstract
We introduce the Learning Feed-Forward Control configuration. In this configuration, a B-spline neural network is contained, which suffers from the curse of dimensionality. We propose a method to avoid the occurrence of this problem.Manuscript from author [PDF]
A. Schierwagen, H. Werner
Abstract
not yet availableScanned document [PDF]
J. Suykens, J. Vandewalle
Abstract
not yet availableScanned document [PDF]
T. Kolb, W. Ilg, J. Wille
Abstract
not yet availableScanned document [PDF]
M. Crucianu, Z. Uhry, J.-P. Asselin de Beauville, R. Bone
Abstract
We extend the Bayesian framework to Multi-Layer Perceptron models of Non-linear Auto-Regressive time-series. The approach is evaluated on an artificial time-series and some common simplifications are discussed.Manuscript from author [PDF]
K. Schaedler, F. Wysotzki
Abstract
not yet availableScanned document [PDF]
G. P. Klebus
Abstract
not yet availableScanned document [PDF]
M. Fernandez, C. Hernandez
Abstract
not yet availableScanned document [PDF]
M. Fernandez, C. Hernandez
Abstract
not yet availableScanned document [PDF]
L. Boquete, R. Barea, M. Mazo, I. Aranda
Abstract
not yet availableScanned document [PDF]
J. Feng, D. Brown
Abstract
not yet availableScanned document [PDF]
A. Karniel, R. Meir, G.F. Inbar
Abstract
Feed-forward control schemes require an inverse mapping of the controlled system. In adaptive systems as well as in biological modeling this inverse mapping is learned from examples. The biological motor control is very redundant, as are many robotic systems, implying that the inverse problem is ill posed. In this work a new architecture and algorithm for learning multiple inverses is proposed, the polyhedral mixture of linear experts (PMLE). The PMLE keeps all the possible solutions available to the controller in real time. The PMLE is a modified mixture of experts architecture, where each expert is linear and more than a single expert may be assigned to the same input region.The learning is implemented by the hinging hyperplanes algorithm. The proposed architecture is described and its operation is illustrated for some simple cases.Manuscript from author [PDF]
A. Krawiecki, R.A. Kosinski
Abstract
not yet availableScanned document [PDF]
T. Koskela, M. Varsta, J. Heikkonen, K. Kaski
Abstract
Recurrent Self-Organizing Map (RSOM) is studied in three different time series prediction cases. RSOM is used to cluster the series into local data sets, for which corresponding local linear models are estimated. RSOM includes recurrent difference vector in each unit which allows storing context from the past input vectors. Multilayer perceptron (MLP) network and autoregressive (AR) model are used to compare the prediction results. In studied cases RSOM shows promising results.Manuscript from author [PDF]
A. Sadeghi
Abstract
not yet availableScanned document [PDF]
A. Rauber, D. Merkl
Abstract
not yet availableScanned document [PDF]
S. Kaski, J. Nikkila, T. Kohonen
Abstract
not yet availableScanned document [PDF]
T. Villmann, M. Herrmann
Abstract
not yet availableScanned document [PDF]
E. Merényi
Abstract
The mineralogic composition of planetary surfaces is often mapped from remotely sensed spectral images. Advanced hyperspectral sensors today provide more detailed and more voluminous measurements than traditional classification algorithms can efficiently exploit. ANNs, and specifically Self-Organizing Maps, have been used at the Lunar and Planetary Laboratory, University of Arizona,to address these challenges.Manuscript from author [PDF]
S. Bermejo, J. Cabestany, M. Payeras
Abstract
not yet availableScanned document [PDF]
J.A. Flanagan
Abstract
not yet availableScanned document [PDF]
S. McGlinchey, C. Fyfe
Abstract
not yet availableScanned document [PDF]
A. Lendasse, M. Verleysen, E. de Bodt, M. Cottrell, P. Grégoire
Abstract
In this paper, we propose a generic non-linear approach for time series forecasting. The main feature of this approach is the use of a simple statistical forecasting in small regions of an input space adequately chosen and quantized. The partition of the space is achieved by the Kohonen algorithm. The method is then applied to a widely known time-series from the SantaFe competition, and the results are compared with the best ones published for thisManuscript from author [PDF]
C. Wellekens
Abstract
As an introduction to a session dedicated to neural networks in speech processing, this paper describes the basic problems faced with in automatic speech recognition (ASR). Representation of speech, classification problems, speech unit models, training procedures and criteria are discussed. Why and how neural networks lead to challenging results in ASR is explained.Manuscript from author [PDF]
M. Kurimo
Abstract
not yet availableScanned document [PDF]
D. Willett, G. Rigoll
Abstract
not yet availableScanned document [PDF]
J. Fritsch, A. Waibel
Abstract
not yet availableScanned document [PDF]
B. Hammer
Abstract
In this paper we show that the loading problem for a $3$-node architecture with sigmoidal activation is NP-hard if the input dimension varies, if the classification is performed with a certain accuracy, and if the output weights are restricted.Manuscript from author [PDF]
P. Edwards, A. Murray
Abstract
not yet availableScanned document [PDF]
D. Perrotta
Abstract
not yet availableScanned document [PDF]
A. Poncet, A. Deiss, S. Holles
Abstract
not yet availableScanned document [PDF]
P. Thomas, G. Bloch, C. Humbert
Abstract
not yet availableScanned document [PDF]
A. Alessandri, M. Maggiore, M. Sanguineti
Abstract
not yet availableScanned document [PDF]
T. Roska
Abstract
not yet availableScanned document [PDF]
B. Mirzai, D. Lim, G.S. Moschyts
Abstract
not yet availableScanned document [PDF]
Y. Moreau, J. Vandewalle
Abstract
not yet availableScanned document [PDF]
P. Arena, L. Fortuna
Abstract
not yet availableScanned document [PDF]
I. Aizenberg, N. Aizenberg, E. Gotko, J. Vandewalle
Abstract
not yet availableScanned document [PDF]
C.G. Puntonet, M.R. Alvarez, A. Prieto, B. Prieto
Abstract
not yet availableScanned document [PDF]
S. Hosseini, C. Jutten
Abstract
not yet availableScanned document [PDF]
M. Spratling, G. Hayes
Abstract
This paper presents a novel self-organising neural network. It has been developed for use as a simplified model of cortical development. Unlike many other models of topological map formation all synaptic weights start at zero strength (so that synaptogenesis might be modelled). In addition, the algorithm works with the same format of encoding for both inputs to and outputs from the network (so that the transfer and recoding of information between cortical regions might be modelled).Manuscript from author [PDF]
M. Spratling, G. Hayes
Abstract
This paper shows how the relationship between two arrays of artificial neurons, representing different cortical regions, can be learned. The algorithm enables each neural network to self-organise into a topological map of the domain it represents at the same time as the relationship between these maps is found. Unlike previous methods learning is achieved without a separate training phase; the algorithm which learns the mapping is also that which performs the mapping.Manuscript from author [PDF]
T. Seiler, V. Stephan, H.-M. Gross
Abstract
not yet availableScanned document [PDF]
G. Rotundo, B. Tirozzi, M. Valente
Abstract
not yet availableScanned document [PDF]
V. Colla, M. Sgarbi, L.M. Reyneri, A.M. Sabatini
Abstract
not yet availableScanned document [PDF]
Pei Ling Lai, C. Fyfe
Abstract
not yet availableScanned document [PDF]
R. Raducanu, M. Grana, A. D'Anjou, F.X. Albizuri
Abstract
not yet availableScanned document [PDF]
A. Rogozan, P. Deleglise
Abstract
This paper describes a new approach for visual speech recognition (also called speechreading) using hybrid HMM/NN models. First, we use the Self-Organising Map (SOM) to merge phonemes that appear visually similar into visemes1. Then we develop an hybrid speechreading system with two communicating components: HMM and NN, to take advantage from the qualities of both. The first component is a classical continuous HMM, while the second one is the Time Delay Neural Network (TDNN) or the Jordan partially recurrent Neural Network (JNN). At the beginning of the recognition process the HMM component segments and labels the visual data. In the case of visemes which are often confused by using the HMM, but rarely with the NN, we use the NN component to label the corresponding boundaries. For the other visemes, the final response is given by the HMM component. Finally, we evaluate the hybrid system on a continuously spelling task and we show that it outperform an HMM system and a NN one.Scanned document [PDF]
E. Drege, F. Yang, M. Paindavoine, H. Abdi
Abstract
not yet availableScanned document [PDF]
S. Gutta, H. Wechsler
Abstract
not yet availableScanned document [PDF]
S. Oka, M. Kitabata, Y. Ajioka, Y. Takefuji
Abstract
not yet availableScanned document [PDF]
F. Maghrebi
Abstract
not yet availableScanned document [PDF]
E. Mulder, H.A.K. Mastebroeck
Abstract
not yet availableScanned document [PDF]
J.A. Walter
Abstract
not yet availableScanned document [PDF]