HUSCAP logo Hokkaido Univ. logo

Hokkaido University Collection of Scholarly and Academic Papers >
情報科学研究科  >
雑誌発表論文等  >

Transfer learning based on the observation probability of each attribute

smc2014suzuki.pdf547.03 kBPDF見る/開く

タイトル: Transfer learning based on the observation probability of each attribute
著者: Suzuki, Masahiro 著作を一覧する
Sato, Haruhiko 著作を一覧する
Oyama, Satoshi 著作を一覧する
Kurihara, Masahito 著作を一覧する
キーワード: transfer learning
multiclass classification
incremental learning
generative model
発行日: 2014年
出版者: IEEE (Institute of Electrical and Electronics Engineers)
引用: 2014 IEEE International Conference on Systems, Man, and Cybernetics (SMC), ISBN: 978-1-4799-3840-7
開始ページ: 3627
終了ページ: 3631
出版社 DOI: 10.1109/SMC.2014.6974493
抄録: Machine learning is the basis of important advances in artificial intelligence. Unlike the general methods of machine learning, which use the same tasks for training and testing, the method of transfer learning uses different tasks to learn a new task. Among the various transfer learning algorithms in the literature, we focus on the attribute-based transfer learning. This algorithm realizes transfer learning by introducing attributes and transferring the results of training to another task with the common attributes. However, the existing method does not consider the frequency in which each attribute appears in feature vectors (called the observation probability). In this paper, we present a generative model with the observation probability. By the experiments, we show that the proposed method has achieved a higher accuracy rate than the existing method. Moreover, we see that it makes possible the incremental learning that was impossible in the existing method.
Rights: © 2014 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
資料タイプ: proceedings (author version)
出現コレクション:雑誌発表論文等 (Peer-reviewed Journal Articles, etc)

提供者: 小山 聡


本サイトに関するご意見・お問い合わせは repo at へお願いします。 - 北海道大学