Machine Learning Foundations 课程由台湾大学NTU林轩田老师开设，课程共16篇，包括四部分内容：
- When can machines learn? (illustrative + technical)
- Why can machines learn? (theoretical + technical)
- How can machines learn? (technical + practical)
- How can machines learn better? (practical + theoretical)
下面是Topic 1 Part 1——the learning problem
0. Course Introduction
foundation oriented and story-like
1. What is Machine Learning
- learning VS Machine Learning
- learning: observations -> learning -> skill
- Machine Learning: data -> ML -> skill
- skill: import some performace measure, 提高某一性能
- 使用ML的三个关键条件：
- 事物本身存在某种规律
- 难以通过简单编程解决
- 有数据可供使用
2. Applications of Machine Learning
ML is everywhere
食、衣、住、行、育、乐
3. Components of Machine Learning
- 基本术语
- hypothesis g VS target f
- f是目标函数，反映问题的真实规律，但f一般是未知的；
- g是通过算法A得出的假设函数，我们希望g尽可能与f接近
- hypothesis set H 假设集，一般一个问题对应了多个假设，这些假设形成假设集H，从H中找出最佳的g。
- ML流程图
- 训练数据D满足未知的目标函数f
- 机器学习的过程，就是根据先验知识选择模型，该模型对应的hypothesis set（用H表示），H中包含了许多不同的hypothesis，通过演算法A，在训练样本D上进行训练，选择出一个最好的hypothesis，对应的函数表达式g就是我们最终要求的。
- Machine Learning: use data to compute hypothesis g that approximates target f
- A takes D and H to get g
4. Machine Learning and Other Fields
与ML相关的领域：
- Data Mining: use (huge) data to find property that is interesting
difficult to distinguish ML and DM in reality - Artificial Intelligence: compute something that shows intelligent behavior
ML is one possible route to realize AI - Statistics: use data to make inference about an unknown process
many useful tools for ML
