METHOD FOR STUDY USING EXTRACTED CHARACTERISTIC OF DATA AND APPARATUS THEREOF

摘要

Disclosed is a learning method using extracted data characteristics for simplifying learning process and improving the accuracy of the estimation. The learning method using the extracted data characteristics comprises the steps of: dividing input learning data into two groups on the criteria set in advance; extracting the data characteristics that can distinguish the divided groups; and performing a learning by using the extracted characteristics. The present invention can simplify the learning process and improve the accuracy of the estimation because the learning data is classified in stages for extracting the characteristics that can easily distinguish each group. [Reference numerals] (AA) Start; (BB) Yes; (CC) No; (DD) End; (S110) Dividing input learning data into two groups; (S120) Extracting the data characteristics that can distinguish the divided groups; (S130) Division of sub-groups is necessary?; (S140) Diving to the sub-groups; (S150) Learning by using the extracted characteristics