一种改进的深度神经网络应用于推荐系统  

An improved deep neural network is applied for recommendation system

作　　者：龚道庆 曹爱清 Gong Daoqing;Cao Aiqing(Nanning Normal University,Nanning 530023,China)

机构地区：[1]南宁师范大学,广西南宁530023

出　　处：《无线互联科技》2020年第4期40-41,共2页Wireless Internet Technology

摘　　要：推荐系统是信息过滤的一种重要工具。随着互联网和大数据的介入,推荐系统的技术革新面临着新的挑战。近年来,深度学习的革命性进步在语音识别、图像分析和自然语言处理方面都受到了广泛关注。与此同时,一种应用于许多复杂任务的最先进的机器学习技术被用于推荐系统,以提高推荐的质量。由于其一流的性能表现和高质量的推荐结果,深度学习可以更好地理解用户需求、项目特征及其之间的历史性互动。文章提出将一种改进的深度神经网络应用于推荐系统。实验结果表明,该方法的效果令人瞩目。Recommendation system is an important tool for information filtering.With the intervention of Internet and big data,the technical innovation of recommendation system is facing new challenges.In recent years,revolutionary advances in deep learning have attracted a lot of attention in speech recognition,image analysis and natural language processing.At the same time,a state-ofthe-art machine learning technology applied to many complex tasks is used in recommendation systems to improve the quality of recommendations.Due to its first-class performance and high-quality recommendation results,deep learning can better understand users’ needs,project characteristics and their historical interactions.In this paper,an improved deep neural network is applied to the recommendation system.The experimental results show that the effect of this method is remarkable.

关 键 词：深度神经网络 推荐系统 进化算法 

分 类 号：TP391.3[自动化与计算机技术—计算机应用技术] TP183[自动化与计算机技术—计算机科学与技术]