0


大规模的机器学习:问题,运算法则和挑战

Large-Scale Machine Learning: The Problems, Algorithms, and Challenges
课程网址: http://videolectures.net/nipsworkshops09_gray_lsml/  
主讲教师: Alex Gray
开课单位: 乔治亚理工学院
开课时间: 2010-01-19
课程语种: 英语
中文简介:
为了促成讨论,我将尝试通过研究所有机器学习中常见的计算问题以及为它们创建高效并行算法的挑战,来组织大规模机器学习中的研究工作。我将首先确定在所有机器学习或原型算法问题中出现的四种常见类型的计算瓶颈:n体问题、图运算、线性代数和优化。在每一个类别中,我将讨论我们可以或不能从现有的科学计算工作中学习到什么,重点介绍为具体性开发的一些最成功和最新的特定串行算法,并讨论是什么使它们容易或难并行化。我将综合这些观察结果,以获得并行机器学习算法研究和软件工具包的设计数据列表。
课程简介: To seed discussion, I will attempt to organize research efforts in large-scale machine learning by looking at common computational problems across all of machine learning, and the challenges of creating efficient parallel algorithms for them. I'll begin by identifying four common types of computational bottlenecks that occur across all of machine learning, or prototype algorithmic problems: N-body problems, graph operations, linear algebra, and optimization. Within each category, I'll discuss what we can or cannot learn from the existing body of work in scientific computing, highlight a few of the most successful and recent specific serial algorithms that have been developed for concreteness, and discuss what makes them easy or hard to parallelize. I'll synthesize some of these observations to obtain a list of desiderata for parallel machine learning algorithms research and software toolkits.
关 键 词: 机器学习; N体问题; 图的运算; 线性代数; 和优化
课程来源: 视频讲座网
最后编审: 2020-06-02:毛岱琦(课程编辑志愿者)
阅读次数: 35