基于主动学习的机器学习算法研究进展  

Research Progress of Active Learning Algorithm

作　　者：刘霄宇 左劼[1] 孙频捷[2] LIU Xiao-yu;ZUO Jie;SUN Pin-jie(College of Computer Science,Sichuan University,Chengdu 610065;Shanghai University of Political Science and Law,Shanghai 200000)

机构地区：[1]四川大学计算机学院,成都610065 [2]上海政法学院,上海200000

出　　处：《现代计算机》2021年第3期32-36,共5页Modern Computer

基　　金：国家重点研发计划项目。

摘　　要：主动学习算法的目的是通过算法模型与标注人员的交互,使标注人员只使用少量的数据便可以获得与大量数据相同的模型预测准确率。近年来,主动学习算法在各种数据的标注获取、训练算法模型的过程中起到巨大的作用,有效地降低标注成本,这引起学者们的广泛关注与深入研究。通过对主动学习算法在图像分类任务中的方法进行归纳分析与整理,为基于主动学习的机器学习方法提供理论依据。The purpose of the active learning algorithm is to interact with the annotator through the algorithm model,so that the annotator can obtain the same model prediction accuracy rate as a large amount of data using only a small amount of data.In recent years,active learning algo⁃rithms have played a huge role in the process of labeling various data and training algorithm models,effectively reducing the cost of label⁃ing,which has attracted widespread attention and in-depth research by scholars.Through the inductive analysis and sorting of the methods of active learning algorithms in image classification tasks,it provides a theoretical basis for machine learning methods based on active learning.

关 键 词：主动学习 机器学习 表征学习 深度学习 

分 类 号：TP181[自动化与计算机技术—控制理论与控制工程]