ZhouYongyi's Personal Blog

# 吴恩达《机器学习》课程学习笔记（一）—— 绪论

## 前言

“吴恩达《机器学习》课程学习笔记”这个系列，是用来记录学习Coursera版本过程中的内容的。限于我仍是机器学习的初学者，在笔记过程中难免会出现思路、方法的不周之处。如果对笔记中的公式、内容有疑问，请先到Coursera查看吴恩达教授的讲义。

## 一、什么是机器学习（Machine Learning）？

1.Arthur Samuel提出的定义：

“The field of study that gives computers the ability to learn without being explicitly programmed.”

Arthur Samuel认为，机器学习致力于让计算机在没有明确地编程的情况下有能力进行学习。这是一种老旧、不正式的定义。（他曾让电脑自己进行双方博弈，判断哪种棋局赢面更大。通过这样的方法，最终得到了一个厉害的下棋程序。）

2.Tom Mitchell提出的定义：

“A computer program is said to learn from experience E with respect to some class of tasks T and performance measure P, if its performance at tasks in T, as measured by P, improves with experience E.”

Tom Mitchell认为，从“以某种任务T为目标，以P为性能指标的经验E中”进行学习的计算机程序，它在“以任务T为目标，P为性能指标”的情况下，表现会随着“经验E”的增长而变得更好。Andrew Ng认为这是一个和现在比较相符的定义（尽管他开玩笑Tom Mitchell是为了押韵才这样表述）。

E=玩多局游戏得到的经验

T=跳棋取胜的目标

P=程序赢得游戏的可能性

• Classifying emails as spam or not spam. –T
• Watching you label emails as spam or not spam.- E
• The number(or fraction) of emails correctly classified as spam/not spam.- P

## 二、监督学习（Supervised Learning）

In supervised learning, we are given a data set and already know what our correct output should look like, having the idea that there is a relationship between the input and the output.

• 在回归问题中，我们尝试预测出连续的输出。换句话说，我们是尝试将变量映射到某一个连续函数上。
• 在分类问题中，我们尝试预测出离散的输出。换句话说，我们是尝试将变量映射到某一些离散分类里。

• Problems1: You have a large inventory of identical items. You want to predict how many of these items will sell over next 3 months.
• Problems2: You’d like software to examine individual customer accounts, and for each account decide if it has been hacked/compromised.

Should you treat these as classification or as regression problems?

## 三、无监督学习（Unsupervised Learning）

Unsupervised learning, allows us to approach problems with little or no idea what our results should look like. We can derive structure from data where we don’t necessarily know the effect of the variables.

## 四、编程环境推荐

##### zhouyongyi

DeepLearning.ai上的课是不是包括“神经网络和深度学习”、“改善深层神经网络：超参数调试、正则化以及优化”、“结构化机器学习项目”、“卷积神经网络”、“序列模型”这几门课呢？

##### zhouyongyi

$${}$$