Effectively learn how to learn: a novel few-shot learning with meta-gradient memory

淡江大學機構典藏 > 工學院 > 資訊工程學系暨研究所 > 期刊論文 > Item 987654321/126706

jsp.display-item.identifier=請使用永久網址來引用或連結此文件: https://tkuir.lib.tku.edu.tw/dspace/handle/987654321/126706

题名:	Effectively learn how to learn: a novel few-shot learning with meta-gradient memory
作者:	Hui, Lin
关键词:	machine learning;deep learning;meta-learning;continual learning
日期:	2024-03-25
上传时间:	2025-03-06 14:08:49 (UTC+8)
摘要:	Recently, the importance of few-shot learning has tremendously grown due to its widespread applicability. Via few-shot learning, users can train their models with few data and maintain high generalisation ability. Meta-learning and continual learning models have demonstrated elegant performance in model development. However, unstable performance and catastrophic forgetting are still two fatal issues with regard to retaining the memory of knowledge about previous tasks when facing new tasks. In this paper, a novel method, enhanced model-agnostic meta-learning (EN-MAML), is proposed for blending the flexible adaptation characteristics of meta-learning and the stable performance of continual learning to tackle the above problems. Based on the proposed learning method, users can efficiently and effectively train the model in a stable manner with few data. Experiments show that when following the N-way K-shot experimental protocol, EN-MAML has higher accuracy, more stable performance and faster convergence than other state-of-the-art models on several real datasets.
關聯:	International Journal of Web and Grid Services 20(1),　p.3
DOI:	10.1504/IJWGS.2024.137549
显示于类别:	[資訊工程學系暨研究所] 期刊論文

文件中的档案:

档案	描述	大小	格式	浏览次数
index.html		0Kb	HTML	22	检视/开启

在機構典藏中所有的数据项都受到原著作权保护.

TAIR相关文章