[Machine Learning by Stanford] Introduction - What is Machine Learning

This is a brief summary of ML course provided by Andrew Ng and Stanford in Coursera.

You can find the lecture video and additional materials in 

https://www.coursera.org/learn/machine-learning/home/welcome

Coursera | Online Courses From Top Universities. Join for Free

 

There is no one fixed definition for machine learning. Some examples as below:

Arthur Samuel (1959) - Field of study that gives computers the ability to learn without being explictly programmed. 

Tom Mitchell (1998) - Well-posed Learning Problem: A computer program is said to learn from experience E with respect to some task T and some performace measure P, if its performance on T, as measured by P, improves with experienc E.

 

Quiz: Suppose your email program watches which emails you do or do not mark as spam, and based on that learns how to better filter spam. What is the task T in this setting?

1. Classifying emails as spam or not spam.

2. Watching you label emails as spam or not spam.

3. The number of emails correctly classified as spam/ not spam. 

4. None of the above. 

 

Answer: 1.   

Short explanation: 2 is E (experience) and 3 is P (performance)

 

Another example for Mitchell's definition,

Example: playing checkers.

E = the experience of playing many games of checkers

T = the task of playing checkers.

P = the probability that the program will win the next game.

 

Machine Learning Algorithms:

- Supervised Learning

- Unsupervised Learning

 

Others: Reinforcement Learning, Recommender systems

Also talk about: Practical advice for applying learning algorithms.

Teaching about learning algroithms is like giving a set of tools. 

Equally, or more important than giving you the tools as they teach you how to apply these tools.

 

Imagine that someone is teaching you how to be a carpenter, 

knowing what a hammer, a screwdriver, and a saw is not sufficient. 

--> to learn how to use these tools properly is more important