Machine Learning Series Notes - Preface

Keywords:Machine Learning, Andrew Ng

What is Machine Learning?

Even among machine learning practitioners there isn't a well accepted definition of what is and what isn't machine learning.

Here's two Definitions mentioned in Andrew Ng's video:
Arthur Samuel(1959):

Field of study that gives computers the ability to learn without being explicitly programmed.

Tom Mitchell(1998):

A computer program is said to learn from experience E with respect to some task T and some performance measure P, if its performance on T, as measured by P, improves with experience E.

Here's a classic example may help you to understand:

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

What can Machine Learning do?

Here're some Typical Applications:

• Database mining

  Large datasets from growth of automation/web
  E.g., Web click data, medical records, biology, engineering

• Applications can't program by hand.

  E.g., Autonomous helicopter, handwriting recognition, most of Natural Lanuage Processing(NLP),Computer Vision

• self-customizing programs
  E.g., Amazon,Netflix product recommendations

• Understanding human learning(brain,real AI)

More details you can check out here, if you are interested in.

Prerequisites

Like lots of people said you'd better have some foundations of mathematics, and better know how to program by python.
But you can start from Andrew Ng's online course on coursera, it will help you quickly and smoothly get into ML's world.

Here're some suggestions that make sense for me and you may need that too.

Machine Learning Algorithms

The most commonly used algorithms:

• Supervised Learning
• Unsupervised Learning

Others: Reinforcement learning, recommender systems.

Conclusion

By now, you may have a preliminary but not clearly impression about machine learning. Just don't worry about that. This series of notes will record everything I learn about how to design and build serious machine learning and AI systems. And I hope it would be helpful.

Next

We will start to talk about supervised learning and unsupervised learning, and how to use each of them.

Some tips you may need

If you found you couldn't open the urls above. Here's an easily-use and cheap vps.
Once you need a vps, you probably live in China, so here's a Chinese introduction about how to install a ss quickly.