SIA OpenIR  > 机器人学研究室
Active Lifelong Learning with “Watchdog”
Sun G(孙干)1,2; Cong Y(丛杨)1; Xu XW(徐晓伟)3
Department机器人学研究室
Conference Name32nd AAAI Conference on Artificial Intelligence (AAAI-18)
Conference DateFebruary 2-7, 2018
Conference PlaceNew Orleans, Louisiana, USA
Source Publication32nd AAAI Conference on Artificial Intelligence (AAAI-18)
PublisherAAAI
Publication PlacePalo Alto, USA
2018
Pages4107-4114
Indexed ByEI ; CPCI(ISTP)
EI Accession number20190506435930
WOS IDWOS:000485488904024
Contribution Rank1
AbstractLifelong learning intends to learn new consecutive tasks depending on previously accumulated experiences, i.e., knowledge library. However, the knowledge among different new coming tasks are imbalance. Therefore, in this paper, we try to mimic an effective “human cognition” strategy by actively sorting the importance of new tasks in the process of unknown-to-known and selecting to learn the important tasks with more information preferentially. To achieve this, we consider to assess the importance of the new coming task, i.e., unknown or not, as an outlier detection issue, and design a hierarchical dictionary learning model consisting of two-level task descriptors to sparse reconstruct each task with the _0 norm constraint. The new coming tasks are sorted depending on the sparse reconstruction score in descending order, and the task with high reconstruction score will be permitted to pass, where this mechanism is called as “watchdog”. Next, the knowledge library of the lifelong learning framework encode the selected task by transferring previous knowledge, and then can also update itself with knowledge from both previously learned task and current task automatically. For model optimization, the alternating direction method is employed to solve our model and converges to a fixed point. Extensive experiments on both benchmark datasets and our own dataset demonstrate the effectiveness of our proposed model especially in task selection and dictionary learning.
Language英语
Citation statistics
Document Type会议论文
Identifierhttp://ir.sia.cn/handle/173321/23843
Collection机器人学研究室
Corresponding AuthorSun G(孙干)
Affiliation1.State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences, China
2.University of Chinese Academy of Sciences, China
3.Department of Information Science, University of Arkansas at Little Rock, USA
Recommended Citation
GB/T 7714
Sun G(孙干),Cong Y(丛杨),Xu XW(徐晓伟). Active Lifelong Learning with “Watchdog”[C]. Palo Alto, USA:AAAI,2018:4107-4114.
Files in This Item: Download All
File Name/Size DocType Version Access License
Active Lifelong Lear(1144KB)会议论文 开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Sun G(孙干)]'s Articles
[Cong Y(丛杨)]'s Articles
[Xu XW(徐晓伟)]'s Articles
Baidu academic
Similar articles in Baidu academic
[Sun G(孙干)]'s Articles
[Cong Y(丛杨)]'s Articles
[Xu XW(徐晓伟)]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Sun G(孙干)]'s Articles
[Cong Y(丛杨)]'s Articles
[Xu XW(徐晓伟)]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: Active Lifelong Learning with “Watchdog”.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.