Kohonen Networks. Kohonen Neural network. Introduction The cerebral cortex is arguably the most fascinating structure in all of human physiology. Although vastly complex on a microscopic level, the cortex reveals a consistently uniform structure on a macroscopic scale, from one brain to another. Centers for such diverse activities as thought, speech, vision, hearing, and motor functions lie in specific areas of the cortex, and these areas are located consistently relative to one another. Moreover, individual areas exhibit a logical ordering of their functionality. An example is the so-called tonotopic map of the auditory regions, where neighboring neurons respond to similar sound frequencies in an orderly sequence from high pitch to low pitch. It appears likely that our genetic makeup predestines our neural development to a large extent. The cortex is essentially a large (approximately 1-meter-square, in adult humans) thin (2-to-4-millimeter thick) sheet consisting of six layers of neurons of varying type and density.
Kohonen.pdf (Objet application/pdf) Kohonen network. Figure 1: The array of nodes in a two-dimensional SOM grid. The Self-Organizing Map (SOM), commonly also known as Kohonen network (Kohonen 1982, Kohonen 2001) is a computational method for the visualization and analysis of high-dimensional data, especially experimentally acquired information. Introduction The Self-Organizing Map defines an ordered mapping, a kind of projection from a set of given data items onto a regular, usually two-dimensional grid. A modelm_i is associated with each grid node ( Figure 1). These models are computed by the SOM algorithm.
Like a codebook vector in vector quantization, the model is then usually a certain weighted local average of the given data items in the data space. History The SOM algorithm grew out of early neural network models, especially models of associative memory and adaptive learning (cf. Figure 2: Left image: Models of acoustic spectra of Finnish phonemes, organized on an SOM. Mathematical definition of the SOM Software packages References. Kohonen.pdf (Objet application/pdf) Carte auto adaptative. Un article de Wikipédia, l'encyclopédie libre. Les cartes auto adaptatives ou auto organisatrices forment une classe de réseau de neurones artificiels fondée sur des méthodes d'apprentissage non-supervisées. On les désigne souvent par le terme anglais self organizing maps (SOM), ou encore cartes de Teuvo KohonenTeuvo Kohonen du nom du statisticien ayant développé le concept en 1984.
Elles sont utilisées pour cartographier un espace réel, c'est-à-dire pour étudier la répartition de données dans un espace à grande dimension. En pratique, cette cartographie peut servir à réaliser des tâches de discrétisation, quantification vectorielle ou classification. Idée de base[modifier | modifier le code] Techniquement, la carte réalise une quantification vectorielle de l'espace de données. Cela signifie discrétiser l'espace ; c'est-à-dire le diviser en zones, et affecter à chaque zone un point significatif dit vecteur référent. Architecture des cartes auto-organisatrices. Un neurone est rapproché de v.