摘要
深度学习技术是机器学习领域的一个研究热点,已被深入研究并广泛应用于许多领域.推荐系统是缓解信息过载的重要技术,如何将深度学习融入推荐系统,利用深度学习的优势从各种复杂多维数据中学习用户和物品的内在本质特征,构建更加符合用户兴趣需求的模型,以提高推荐算法的性能和用户满意度,是深度学习应用于推荐系统的主要研究任务.对基于深度学习的推荐算法研究和应用现状进行了综述,讨论并展望了深度学习应用于推荐系统的研究发展趋势.
Deep learning technology has recently become a very hot topic in the machine learning field,and has been thoroughly studied and widely used in many fields.The recommender system is an important technology to alleviate information overload.Deep learning has the advantages of learning the intrinsic characteristics of users and items from various complex multidimensional data.How to integrate deep learning into recommender systems to build a model that is more in line with the user preferences and improving recommendation performance is the main research task of deep learning based recommender systems.In this paper,the research and application of deep learning based recommender algorithms are reviewed,and the future research and development trends of integrating deep learning to recommender systems are discussed.
作者
王俊淑
张国明
胡斌
Wang Junshu;Zhang Guoming;Hu Bin(School of Geography,Nanjing Normal University,Nanjing 210023,China;Key Laboratory of Virtual Geographic Environment of Ministry of Education,Nanjing Normal University,Nanjing 210023,China;Department of Computer Science and Technology,Nanjing University,Nanjing 210023,China;Health Statistics and Information Center of Jiangsu Province,Nanjing 210008,China)
出处
《南京师范大学学报（工程技术版）》
CAS
2018年第4期33-43,共11页
Journal of Nanjing Normal University(Engineering and Technology Edition)
基金
国家自然科学基金(41571389)
江苏省自然科学基金(BK20171037)
江苏省高校自然科学研究面上项目(17KJB420003)
关键词
推荐系统
深度学习
协同过滤
内容推荐
动态推荐
标签推荐
recommender systems
deep learning
collaborative filtering
content-based recommendation
dynamic recommendation
tag-based recommendation
