理解《A Survey on Transfer Learning》

最新推荐文章于 2023-04-25 16:32:53 发布

TayYoung

最新推荐文章于 2023-04-25 16:32:53 发布

阅读量5k

点赞数

分类专栏：科研文章标签：机器学习迁移学习综述

本文链接：https://blog.csdn.net/tayyoung/article/details/60869144

版权

本文深入探讨了迁移学习的概念，特别是在不同领域和任务中的应用。通过对比传统机器学习的假设，强调了迁移学习在处理数据分布不一致情况下的优势。文章详细分类并介绍了归纳式、直推式和无监督迁移学习的代表算法，以及它们与领域适应、多任务学习等技术的关系。对于理解和应用迁移学习具有指导意义。

摘要由CSDN通过智能技术生成

理解《A Survey on Transfer Learning》
Pan S J, Yang Q. A Survey on Transfer Learning[J]. IEEE Transactions on Knowledge & Data Engineering, 2010, 22(10):1345-1359.

Abstract—A major assumption in many machinelearning and data mining algorithms is that the training and future data mustbe in the same feature space and have the same distribution. However, in manyreal-world applications, this assumption may not hold. For example, wesometimes have a classification task in one domain of interest, but we onlyhave sufficient training data in another domain of interest, where the latterdata may be in a different feature space or follow a different data distribution.In such cases, knowledge transfer, if done successfully, would greatly improvethe performance of learning by avoiding much expensive data-labeling efforts.In rece