|
所在平台: Coursera |
课程主页: https://www.coursera.org/learn/ntumlone-mathematicalfoundations
课程评论：没有评论
课程名称：机器学习基石上（Machine Learning Foundations）---数学基础 课程概述：机器学习研究如何让计算机通过从观察到的数据中积累经验，以自适应方式提升其性能。我们的两门姊妹课程教授任何机器学习用户所需了解的最基本的算法、理论和实用工具。本课程将主要关注数学工具，而另一门课程将更侧重于算法工具。 课程大纲： 1. 第一讲：学习问题 描述：介绍机器学习的定义及其与应用和其他领域的关联。 2. 第二讲：学习回答是/否 描述：您的第一个学习算法（也是世界上第一个！），通过根据数据自适应地搜索选择一个良好的界限来区分“是”和“否”。 3. 第三讲：学习的类型 描述：学习在不同应用中有多种可能性，我们将重点关注从一批带有具体特征的监督数据中进行的二元分类或回归。 4. 第四讲：学习的可行性 描述：当有足够的统计数据和有限数量的假设时，学习可以是“可能近似正确”的。 5. 第五讲：训练与测试 描述：我们在选择训练期间的假设时所付出的代价：表示有效选择数量的增长函数。 6. 第六讲：泛化理论 描述：如果有足够的数据且增长函数增长得不太快，测试误差可以近似训练误差。 7. 第七讲：VC维度 描述：学习发生在模型复杂度有限（称为VC维度）、数据足够和训练误差较低的情况下。 8. 第八讲：噪声与误差 描述：在噪音环境中和不同误差度量下，学习依然能够发生。 该课程旨在为学习机器学习的学员提供坚实的数学基础，使其能够有效地理解和应用机器学习技术。
Name:第一講：The Learning Problem
Description:what machine learning is and its connection to applications and other fields
Name:第二講：Learning to Answer Yes/No
Description:your first learning algorithm (and the world's first!) that "draws the line" between yes and no by adaptively searching for a good line based on data
Name:第三講：Types of Learning
Description:learning comes with many possibilities in different applications, with our focus being binary classification or regression from a batch of supervised data with concrete features
Name:第四講：Feasibility of Learning
Description:learning can be "probably approximately correct" when given enough statistical data and finite number of hypotheses
Name:第五講：Training versus Testing
Description:what we pay in choosing hypotheses during training: the growth function for representing effective number of choices
Name:第六講: Theory of Generalization
Description:test error can approximate training error if there is enough data and growth function does not grow too fast
Name:第七講: The VC Dimension
Description:learning happens if there is finite model complexity (called VC dimension), enough data, and low training error
Name:第八講: Noise and Error
Description:learning can still happen within a noisy environment and different error measures
Machine learning is the study that allows computers to adaptively improve their performance with experience accumulated from the data observed. Our two sister courses teach the most fundamental algorithmic, theoretical and practical tools that any user of machine learning needs to know. This first course of the two would focus more on mathematical tools, and the other course would focus more on algorithmic tools. [機器學習旨在讓電腦能由資料中累積的經驗來自我進步。我們的兩項姊妹課程將介紹各領域中的機器學習使用者都應該知道的基礎演算法、理論及實務工具。本課程將較為著重數學類的工具，而另一課程將較為著重方法類的工具。]
