DC Field | Value | Language |
---|---|---|
dc.contributor.author | Lee, Chanha | ko |
dc.contributor.author | Jeon, Minsu | ko |
dc.contributor.author | Yang, Eunju | ko |
dc.contributor.author | Kim, Seong Hwan | ko |
dc.contributor.author | Youn, Chan-Hyun | ko |
dc.date.accessioned | 2019-11-29T07:23:16Z | - |
dc.date.available | 2019-11-29T07:23:16Z | - |
dc.date.created | 2019-11-25 | - |
dc.date.created | 2019-11-25 | - |
dc.date.created | 2019-11-25 | - |
dc.date.created | 2019-11-25 | - |
dc.date.issued | 2019-10-16 | - |
dc.identifier.citation | 10th International Conference on Information and Communication Technology Convergence (ICTC) - ICT Convergence Leading the Autonomous Future, pp.910 - 915 | - |
dc.identifier.issn | 2162-1233 | - |
dc.identifier.uri | http://hdl.handle.net/10203/268718 | - |
dc.description.abstract | Recently, continual learning is a new training strategy based on replaying memory and allowing beneficial effects to previous tasks. To preserve old information, current continual learning scheme accumulates observed examples into limited buffer or repeatedly trains generative model. This idea of learning scheme is effective to reduce catastrophic forgetting which is deterioration in overall performance when training sequentially. However, there still exists the problem of imbalanced data distribution in limited buffer and it is hard to apply on real-time system due to too long time to train both generative model and classification model. In this paper, we propose sample selection algorithm based on iterative k-means algorithm to improve the memory based continual learning. This approach selects examples to store into a buffer in a unsupervised manner using k-means cluster information. Our experiments on a variant of MNIST and CIFAR-100 datasets show the effects on classification accuracy performance when compared to the state-of-the-art. | - |
dc.language | English | - |
dc.publisher | The korean institue of communications and information sciences (KICS) | - |
dc.title | Imbalanced-Free Memory Selection Scheme Based Continual Learning by Using K-means Clustering | - |
dc.type | Conference | - |
dc.identifier.wosid | 000524690200209 | - |
dc.identifier.scopusid | 2-s2.0-85078287588 | - |
dc.type.rims | CONF | - |
dc.citation.beginningpage | 910 | - |
dc.citation.endingpage | 915 | - |
dc.citation.publicationname | 10th International Conference on Information and Communication Technology Convergence (ICTC) - ICT Convergence Leading the Autonomous Future | - |
dc.identifier.conferencecountry | KO | - |
dc.identifier.conferencelocation | Ramada Plaza Jeju Ocean Front, Jeju Island | - |
dc.identifier.doi | 10.1109/ICTC46691.2019.8939828 | - |
dc.contributor.localauthor | Youn, Chan-Hyun | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.