并行机器学习算法基础体系前沿进展综述  

Recent advances in infrastructure architecture of parallel machine learning algorithms

作　　者：刘斌[1] 何进荣[1] 耿耀君[1] 王最[2] LIU Bin;HE Jinrong;GENG Yaojun;WANG Zui(College of Information Engineering, Northwest A&F University, Yangling, Shaanxi 712100, China;Library, Northwest A&F University, Yangling, Shaanxi 712100, China)

机构地区：[1]西北农林科技大学信息工程学院,陕西杨凌712100 [2]西北农林科技大学图书馆,陕西杨凌712100

出　　处：《计算机工程与应用》2017年第11期31-38,89,共9页Computer Engineering and Applications

基　　金：国家自然科学基金(No.61602388);陕西省博士后基金(No.2016BSHEDZZ121);中央高校基本科研业务费专项资金(No.2452015194;No.2452016081)

摘　　要：大数据环境下,机器学习算法受到前所未有的重视。总结和分析了传统机器学习算法在海量数据场景下出现的若干问题,基于当代并行机分类回顾了国内外并行机器学习算法的研究现状,并归纳总结了并行机器学习算法在各种基础体系下存在的问题。针对大数据环境下并行机器学习算法进行了简要的总结,并对其发展趋势作了展望。With the development of big data,machine learning algorithms have received unprecedented attention.This paper makes a summary and analysis of several problems about parallel machine learning algorithms in big data,then provides an overview of the recent advances in parallel machine learning algorithms based on modern parallel computers.This paper also concludes and summarizes the existing problem in infrastructure architecture of parallel machine learning algorithms.The paper highlights the recent progress and challenges in parallel machine algorithms for big data and discusses on some future directions.

关 键 词：并行计算 机器学习算法 多核 集群 混合体系 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]