Coursera: Machine Learning
课程简介
- 所属大学：Stanford
- 先修要求：AI 入门 + 熟练使用 Python
- 编程语言：Python
- 课程难度：🌟🌟🌟
- 预计学时：100 小时
说起吴恩达，在 AI 届应该无人不晓。他是著名在线教育平台 Coursera 的创始人之一，同时也是 Stanford 的网红教授。这门机器学习入门课应该算得上是他的成名作之一（另一个是深度学习课程），在 Coursera 上拥有数十万的学习者（注意这是花钱买了证书的人，一个证书几百刀），白嫖学习者数量应该是另一个数量级了。
这门课对新手极其友好，吴恩达拥有把机器学习讲成 1+1=2 一样直白的能力。你将会学习到线性回归、逻辑回归、支持向量机、无监督学习、降维、异常检测和推荐系统等等知识，并且在编程实践中夯实自己的理解。作业质量自然不必多言，保姆级代码框架，作业背景也多取自生活，让人学以致用。
当然，这门课作为一个公开慕课，难度上刻意放低了些，很多数学推导大多一带而过，如果你有志于从事机器学习理论研究，想要深究这些算法背后的数学理论，可以参考 CS229 和 CS189。
课程资源
- 课程网站：https://www.coursera.org/learn/machine-learning
- 课程视频：参见课程网站
- 课程教材：无
- 课程作业：参见课程网站
资源汇总
当时重装系统误删了文件，我的代码实现消失在了磁盘的 01 串中。不过这门课由于太过出名，网上想搜不到答案都难，相关课程资料 Coursera 上也一应俱全。
Last update: April 3, 2022
Coursera: Machine Learning
Descriptions
- Offered by: Stanford
- Prerequisites: entry level of AI and proficient in Python
- Programming Languages: Python
- Difficulty: 🌟🌟🌟
- Class Hour: 100 hours
When it comes to Andrew Ng, no one in the AI community should be unaware of him. He is one of the founders of the famous online education platform Coursera, and also a famous professor at Stanford. This introductory machine learning course must be one of his famous works (the other is his deep learning course), and has hundreds of thousands of learners on Coursera (note that these are people who paid for the certificate, which costs several hundred dollars), and the number of nonpaying learners should be far more than that.
The class is extremely friendly to novices, and Andrew has the ability to make machine learning as straightforward as 1+1=2. You'll learn about linear regression, logistic regression, support vector machines, unsupervised learning, dimensionality reduction, anomaly detection, and recommender systems, etc. and solidify your understanding with hands-on programming. The quality of the assignments needs no word to say. With detailed code frameworks and practical background, you can use what you've learned to solve real problems.
Of course, as a public mooc, the difficulty of this course has been deliberately lowered, and many mathematical derivations are skimmed over. If you are interested in machine learning theory and want to investigate the mathematical theory behind these algorithms, you can refer to CS229 and CS189.
Course Resources
- Course Website: https://www.coursera.org/learn/machine-learning
- Recordings: refer to the course website
- Textbook: None
- Assignments: refer to the course website
Personal Resources
My implementation is lost in system reinstallation. However, the course is so famous that you can easily find related resoures online. Also, course material is available on Coursera.
Last update: September 22, 2022