Login| Sign Up| Help| Contact|

Patent Searching and Data


Title:
【発明の名称】ハイアラーキー ニューラル ネットワークに用いる分類方法及びネットワーク
Document Type and Number:
Japanese Patent JP3088766
Kind Code:
B2
Abstract:
Classification procedure implemented in a tree-like neural network which, in the course of learning steps, determines with the aid of a tree-like structure the number of neurons and their synaptic coefficients required for the processing of problems of classification of multi-class examples. Each neuron tends to distinguish, from the examples, two groups of examples approximating as well as possible to a division into two predetermined groups of classes. This division can be obtained through a principal component analysis of the distribution of examples. The neural network comprises a directory of addresses of successor neurons which is loaded in learning mode then read in exploitation mode. A memory stores example classes associated with the ends of the branches of the tree.

Inventors:
Takeshi Chonan
Jean-Pierre Nadal
Application Number:
JP3905191A
Publication Date:
September 18, 2000
Filing Date:
February 12, 1991
Export Citation:
Click for automatic bibliography generation   Help
Assignee:
Konin Krekka Philips Electronics NV
International Classes:
G06F15/18; G06G7/60; G06N3/04; G06N99/00; (IPC1-7): G06F15/18; G06G7/60
Domestic Patent References:
JP340170A
JP2211576A
JP1286040A
JP1243181A
JP63298523A
Other References:
1986 International Conference On Pattern Recognition p849−852
1989 IEEE International Conference On Systems,Man and Cybernetics Vol.3 p915−920
computer methods ahd programs in biomedicine VOLUME23,NUMBER3 DEC.1986 p231−235
Journal of Physics A Mathematical and General Vol.22 No.12 21 June 1989 p2191−2203
NETWORK−COMPUTING IN NEURAL SYSTEMS Vol.1 No.4 p423−438 1990(参考)
Attorney, Agent or Firm:
Akihide Sugimura (5 outside)



 
Previous Patent: 線 香

Next Patent: ドットクロック周波数検出回路