Title:
学習方法、学習プログラムおよび学習装置
Document Type and Number:
Japanese Patent JP7230521
Kind Code:
B2
Abstract:
A learning device(100) generates a first feature value and a second feature value by inputting original training data to a first neural network included in a learning model. The learning device(100) learns at least one parameter of the learning model and a parameter of a decoder, reconstructing data inputted to the first neural network, such that reconstruction data outputted from the decoder by inputting the first feature value and the second feature value to the decoder becomes close to the original training data, and that outputted data that is outputted from a second neural network, included in the learning model by inputting the second feature value to the second neural network becomes close to correct data of the original training data.
Inventors:
Takashi Kato
Kento Uemura
Yu Yasutomi
Kento Uemura
Yu Yasutomi
Application Number:
JP2019006133A
Publication Date:
March 01, 2023
Filing Date:
January 17, 2019
Export Citation:
Assignee:
富士通株式会社
International Classes:
G06N3/084; G06N3/04; G06N20/00
Domestic Patent References:
| JP2018139103A | ||||
| JP2007241895A | ||||
| JP6119431A |
Foreign References:
| WO2018020277A1 |
Other References:
Thomas Robert, Nicolas Thome and Matthieu Cord,HybridNet: Classification and Reconstruction Cooperation for Semi-Supervised Learning,Proceedings of the European Conference on Computer Vision (ECCV) [online],2018年,pp. 153-169, https://openaccess.thecvf.com/content_ECCV_2018/papers/Thomas_Robert_HybridNet_Classification_and_ECCV_2018_paper.pdf,[2022年8月9日検索]
Attorney, Agent or Firm:
Sakai International Patent Office