中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

3 records (took 0.021 seconds)

    Active learning method and system
    1.
    发明专利
    Active learning method and system 未知

    公开(公告)号：GB2423395A

    公开(公告)日：2006-08-23

    申请号：GB0611998

    申请日：2004-10-08

    Applicant: NEC CORP

    Inventor： OSODA TSUTOMU ,  YAMASHITA YOSHIKO

    IPC: G06N3/08 ,  G06N3/00

    Abstract: In an active learning system, known data is sampled and for the known data, learning is performed independently by a plurality of learning machines while for unknown data, next data to be learned is selected. The active learning system includes: a weighting device for performing weighting when sampling known data; a prediction weighting device for performing weighting when integrating the learning results of the learning machines; and a data weighting device for performing weighting when selecting the next data to be learned. Each of the weighting devices performs weighting so as to increase the weight of a ratio when an extreme deviation is present in the data count.

    ACTIVE STUDYING SYSTEM, METHOD AND PROGRAM
    2.
    发明公开
    ACTIVE STUDYING SYSTEM, METHOD AND PROGRAM 审中-公开
    主动学生系统，方法和程序

    公开(公告)号：EP2083379A4

    公开(公告)日：2014-08-27

    申请号：EP07829990

    申请日：2007-10-17

    Applicant: NEC CORP

    Inventor： KUROIWA YUKIKO ,  YAMASHITA YOSHIKO ,  ASOGAWA MINORU

    IPC: G06N5/04 ,  G06N3/00 ,  G06N99/00

    CPC classification number: G06N99/005

    Abstract: A processing unit (2) of an active learning system calculates the degree of similarity of data for which the label value is unknown with respect to data for which the label value is known by using a first data selection section 26, and iterates at least on cycle of the active learning cycle that selects the data to be learned next based on the calculated degree of similarity, to thereby enable finding of the desired data needed for learning a rule more efficiently than a random selection. Thereafter, the processing unit (2) learns a rule based on the data for which the label value is known, and applies the learned rule to a set of unknown data for which the label value is unknown, to shift another active learning cycle that selects the data to be learned next.

Patent Agency Ranking