【00】机器学习之旅启程 Machine Learning Roadmap
【开始我的机器学习之路,感兴趣,就慢慢学,就在CSDN建立自己学习旅程】
指南:
- Learning guide
- Streamlined guide
-
information filter
Scope:
Focus your scope on classification and regression type problems and the relevant algorithms and tools.
-
机器学习的子领域:计算机视觉CV, 自然语言过程NLP, 推荐系统 或 加强学习;
There are subfields of Machine Learning such as Computer Vision, Natural Language Process, Recommender Systems or Reinforcement Learning.These areas can be reduced to classification and regression problems and their study does neatly fit into the roadmap structure that is presented. I would suggest not diving into these fields until you are at the intermediate level.
原则
- 机器学习是一段【旅程】,因此你要只要你现在的位置,以及你的目标是什么?所以你要有耐心去学习,不要急功近利。
- Create semi-formal work products. 以博客帖子,技术文章及代码库来记录自己学习的过程。
- Just-in-time learning. 【用到什么学什么】比如:学习需要的概率论知识和线性代数知识,足以理解就OK了,没有必要在开始机器学习之前去学3年的课程。
-
Leverage existing skills.【现学现用】
If you can code, implement algorithms to understand them rather than studying the math. Use languages you know. Focus on the one thing you are learning, don’t complicate it by learning a new language, tool or library at the same time.
-
Mastery is an ideal.【成为大师是一个目标,理想状态】
Mastery of machine learning requires continuous learning. You can never actually reach it, you can only continue to study, learn and improve.
【3个Tips】
- 【从一个小项目开始学习】Start with a small project that you can complete in one hour.
- 【一周完成一个小的Project】
- 【分享你的成果】Blog, FaceBook,Google+, Github.只要是自己感兴趣的地方。
【我目前的Location】
- 【Beginner】学了Couresera上Andrew的课程,研究生阶段学过一点的《模式识别【国内老师的教育不敢恭维】》
- 【中高级】可以自己参加机器学习大赛,能够编写机器学习的学习包。