Title:
INFORMATION PROCESSING DEVICE, INFORMATION PROCESSING METHOD, AND PROGRAM
Document Type and Number:
WIPO Patent Application WO/2022/249373
Kind Code:
A1
Abstract:
In order to generate an artificial example that more efficiently improves the prediction accuracy of a machine learning model, an information processing device (10) comprises: an acquisition unit (11) that acquires a plurality of training examples; a selection unit (12) that selects two or more training examples in which at least one inaccurate prediction result is obtained by using at least one machine learning model, from among the plurality of training examples, the at least one machine learning model receiving the examples as inputs and outputting the prediction result; and a generation unit (13) that generates an artificial example by combining the two or more training examples selected by the selection unit (12).
Inventors:
HATAKEYAMA YUTA (JP)
OKAJIMA YUZURU (JP)
OKAJIMA YUZURU (JP)
Application Number:
PCT/JP2021/020115
Publication Date:
December 01, 2022
Filing Date:
May 27, 2021
Export Citation:
Assignee:
NEC CORP (JP)
International Classes:
G06N20/00; G06N20/10; G06N20/20
Other References:
ANUBHA KABRA; AYUSH CHOPRA; NIKAASH PURI; PINKESH BADJATIYA; SUKRITI VERMA; PIYUSH GUPTA; BALAJI K: "MixBoost: Synthetic Oversampling with Boosted Mixup for Handling Extreme Imbalance", ARXIV.ORG, 3 September 2020 (2020-09-03), XP081754278
MACIEJ A. CZYZEWSKI: "batchboost: regularization for stabilizing training with resistance to underfitting & overfitting", ARXIV.ORG, 21 January 2020 (2020-01-21), XP081582844
WATANABE, MASATO ET AL.: "Unsupervised annotation target data selection method for active learning", IPSJ TECHNICAL REPORT, vol. 2018, no. 38, 19 September 2018 (2018-09-19), pages 1 - 8, ISSN: 2188-8701, Retrieved from the Internet
MACIEJ A. CZYZEWSKI: "batchboost: regularization for stabilizing training with resistance to underfitting & overfitting", ARXIV.ORG, 21 January 2020 (2020-01-21), XP081582844
WATANABE, MASATO ET AL.: "Unsupervised annotation target data selection method for active learning", IPSJ TECHNICAL REPORT, vol. 2018, no. 38, 19 September 2018 (2018-09-19), pages 1 - 8, ISSN: 2188-8701, Retrieved from the Internet
Attorney, Agent or Firm:
HARAKENZO WORLD PATENT & TRADEMARK (JP)
Download PDF:
Previous Patent: INFORMATION PROCESSING DEVICE, INFORMATION PROCESSING METHOD, AND PROGRAM
Next Patent: BUILDING
Next Patent: BUILDING