Visualization and self-organization of multidimensional data...

Details Visualization and self-organization of multidimensional data... Visualization and self-organization of multidimensional data...

G - Physics

06

K

G06K 9/66 (2006.01) G06K 9/62 (2006.01)

Patent

CA 2312902

The subject system provides reduced-dimension mapping of pattern data. Mapping is applied through conventional single-hidden-layer feed-forward neural network with non-linear neurons. According to one aspect of the present invention, the system functions to equalize and orthogonalize lower dimensional output signals by reducing the covariance matrix of the output signals to the form of a diagonal matrix or constant times the identity matrix. The present invention allows for visualization of large bodies of complex multidimensional data in a relatively "topologically correct" low-dimension approximation, to reduce randomness associated with other methods of similar purposes, and to keep the mapping computationally efficient at the same time.

Le système de l'invention permet de réaliser un mappage à dimensions réduites de données de configuration. Ce mappage est appliqué par le biais d'un réseau neuronal classique à couche simple cachée sans rétroaction muni de neurones non linéaires. Dans un aspect de l'invention, le système est mis en oeuvre pour égaliser et orthogonaliser des signaux de sortie dimensionnels plus faibles par réduction de la matrice de covariance des signaux de sortie relativement à la forme d'une matrice diagonale ou d'une constante multipliée par la matrice unité. Le procédé de l'invention permet de visualiser de grands ensembles de données multidimensionnelles complexes par une approximation des faibles dimensions relativement "topologiquement exacte", en vue de limiter la stochasticité associée à d'autres procédés poursuivant des objectifs similaires et de préserver en même temps l'efficacité computationnelle du mappage.

Affiliated with

Also associated with

Rating

Visualization and self-organization of multidimensional data... does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Visualization and self-organization of multidimensional data..., we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Visualization and self-organization of multidimensional data... will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFCA-PAI-O-2019880