Download scientific diagram | La carte de Kohonen. from publication: Identification of hypermedia encyclopedic user’s profile using classifiers based on. Download scientific diagram| llustration de la carte de kohonen from publication: Nouvel Algorithme pour la Réduction de la Dimensionnalité en Imagerie. Request PDF on ResearchGate | On Jan 1, , Elie Prudhomme and others published Validation statistique des cartes de Kohonen en apprentissage.

Author: Voodoorg Kajirr
Country: Samoa
Language: English (Spanish)
Genre: Science
Published (Last): 27 September 2012
Pages: 284
PDF File Size: 1.35 Mb
ePub File Size: 12.13 Mb
ISBN: 549-7-53908-536-7
Downloads: 83398
Price: Free* [*Free Regsitration Required]
Uploader: Meztijind

Careful comparison of the random initiation approach to principal component initialization for one-dimensional SOM models of principal curves demonstrated that the advantages of principal component SOM initialization are not universal. The training utilizes competitive learning.

La distance cognitive avec le territoire d’origine du produit alimentaire

Anomaly detection k -NN Local outlier factor. The network must be fed a large number of example vectors that represent, as close as possible, the kinds of vectors expected during mapping.

A measurement by the artificial neural networks Kohonen. Ils ont par contre une connaissance correcte des zones de production foie gras, noix, fraise et vin. Journal fe Geophysical Research. Recently, principal component initialization, in which initial map weights are chosen from the space of the first principal components, has become popular due to the exact reproducibility of the results.

  AZ 16-12ZVRK PDF

The artificial neural network introduced by the Finnish professor Teuvo Kohonen in the s is sometimes called a Kohonen map or network. The other way is to think of neuronal weights as pointers to the input space. When the neighborhood has shrunk to just a couple of neurons, the weights are converging to local estimates.

Large SOMs display emergent properties. During mapping, there will be one single winning neuron: Now we need input to feed the map.

This includes matrices, continuous functions or even other self-organizing maps. Artificial neural networks Dimension reduction Cluster analysis algorithms Finnish inventions Unsupervised learning.

Self-organizing map

Avez-vous de la famille en Dordogne? Views Read Edit View history. Archived from the original on Useful extensions include using toroidal grids where opposite edges are connected and using large numbers of nodes. Neural Networks, 77, pp. A self-organizing map SOM or self-organizing feature map SOFM is a type of artificial neural network ANN that is trained using unsupervised learning to produce a low-dimensional typically two-dimensionaldiscretized representation of the input space of the training samples, called a mapand is therefore a method to do dimensionality reduction.

In maps consisting of thousands of nodes, it is possible to perform cluster operations on the map itself.


Self-organizing map – Wikipedia

In the simplest form it is 1 for all neurons close enough to BMU and 0 for others, but a Gaussian function is a common choice, too. For nonlinear datasets, however, random initiation performs better. It is also common to use the U-Matrix. Like most artificial neural networks, SOMs operate in two modes: When a training example is fed to the network, its Euclidean distance to all weight vectors is computed.

Neural networks – A comprehensive foundation 2nd ed. Distance cognitive et territoire.

Enfin, le groupe 4 renforce cette analyse. There are two ways to interpret a SOM.

Cartes auto-organisées pour l’analyse exploratoire de données et la visualisation

Agrandir Original png, 4,9k. If these patterns can be named, the names can be attached to the associated nodes in the trained net. Retrieved from ” https: The network winds up associating output nodes with groups or patterns in the input data set.

In Widrow, Bernard; Angeniol, Bernard.