Abstract
Today, most applications of neural networks are devoted to pattern recognition in the fields of speech and image processing. The main connectionnist tools used for this purpose are associative memories [9], particularly multi-layer networks associated with the well-known algorithm of the backpropagation of the error gradient [10, 11, 13]. To obtain the best results with these devices, it is necessary to apply some preprocessing which increases the orthogonality degree of the prototypes to be stored. For instance, KOHONEN proposed such a preprocessing, very simple but efficient, with a Laplacian filter [9, pp. 170–71]. First, consider these prototypes, that is the input vectors of these memories. In fact, they come from the outputs of sensors (cameras, microphones or eyes, ears and so on…). These sensors are multisensitive: the signal provided by one sensor is a superimposition of signals emitted by all the sources of the neighbourhood. It is clear that decisions and classification of such a set of multidimensional data (prototypes) is difficult or even impossible, because of the redundancy of the components of prototype vectors associated to the mixtures. So, separating the independent sources in these mixtures is a very powerful preprocessing.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
ANS B., GILHODES J.-C., HERAULT J., Simulation de réseaux neuronaux (SIRENE), n - Hypothèse de décodage du message de mouvement porté parles afférences fusoriales la et â par un mécanisme de plasticité synaptique. C. R. Acad. Sc., Paris, 297, série HI, pp 419–22, 1983.
COMON P., Statistical approach to the Jutten-Hérault algorithm for separating independent signals. NATO Advanced Research Workshop on Neuro Computing: Algorithms, Architectures and Applications, Les Arcs, 1989, in this book.
FETY L., Méthodes de traitement d’antenne adaptées aux radiocommunications. Thèse de l’ENST, Paris, 1988.
GOSER K., Basic VLSI Circuits for Neural Networks. NATO Advanced Research Workshop on Neuro Computing: Algorithms, Architectures and Applications, Les Arcs, 1989, in this book.
HERAULT J., JUTTEN C., ANS B., Détection de grandeurs primitives dans un message composite par une architecture de calcul neuromimétique en apprentissage non supervisé. Xème GRETSI, pp. 1017–22, Nice, 1985.
HOUK J. C., RYMER W. Z., CRAGO P. E., Nature of the dynamic response and its relation to the high sensitivity of muscle spindles to small changes in length. In ″Muscle Receptors and Movement″ (H. Taylor and A. Prochazka, Eds.), MacMiUan (London), pp. 33–43, 1981.
JUTTEN C., Calcul Neuromimétique et Traitement du Signal. Analyse en Composantes Indépendantes. Thèse d’état ès Sciences Physiques, INP-USM Grenoble, 1987.
JUTTEN C., HERAULT J., Une solution neuromimétique au problème de séparation de sources. To appear in Traitement du Signal, 1989.
KOHONEN T., Self-Organization and Associative Memory. Springer-Verlag, 1984.
Le CUN Y., A learning scheme for asymétrie threshold network. COGNTITVA 85, pp. 599–604, Paris, 1985.
PARKER D. B., Leaming-Logic. Invention report, S81–64, File 1, Office of Technology Licensing, Standford University, October 1982.
ROLL J.-P., Contribution de la proprioception musculaire à la perception et au contrôle du mouvement chez l’homme. Thèse d’état, Univ. d’Aix-Marseille 1, 1981.
RUMELHART D. E., Me CLELLANDS J. L. and the PDP Research Group. Parallel Distributed Processing: Explorations in the microstructure of cognition. Vol. 1: Foundations.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1990 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Jutten, C., Hérault, J. (1990). Analog implementation of a permanent unsupervised learning algorithm. In: Soulié, F.F., Hérault, J. (eds) Neurocomputing. NATO ASI Series, vol 68. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-76153-9_18
Download citation
DOI: https://doi.org/10.1007/978-3-642-76153-9_18
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-76155-3
Online ISBN: 978-3-642-76153-9
eBook Packages: Springer Book Archive