Got a YouTube account?

New: enable viewer-created translations and captions on your YouTube channel!

English subtitles

← Machine Learning

Video illustrating the description of Andrew Ng's Machine Learning Coursera course. See .

Get Embed Code
3 Languages

Showing Revision 6 created 08/07/2014 by pietergdewaal.

  1. This Fall quarter, Stanford University will be offering online for free
  2. the Machine Learning course that I teach.
  3. Machine Learning has a typical enrolment of 350 students in Stanford
  4. and this is one of the most popular courses offered by the Computer science department.
  5. Over 200'000 people have watched my Machine Learning lectures on YouTube.
  6. Based on this popularity, this year, we're doing something completely new:
  7. We're not just showing you videos, we're inviting you to sign up for
  8. actively participating and take this Stanford class.
  9. What is Machine Learning? You probably use it dozens of times a day,
  10. without even knowing it.
  11. Each time you do a web search on Google or Bing,
  12. that works so well because their machine learning software has figured out how to rank webpages.
  13. When Facebook or Apple's photo application recognizes your friends and your pictures,
  14. that's also machine learning.
  15. Each time you read your email and the spam filter saves you
  16. from having to wade through tons of spam,
  17. again, that's because your computer has learned to distinguish spam from non-spam email.
  18. So, that's machine learning.
  19. It's the science of getting computers to learn without being explicitly programmed.
  20. One of the research projects that I'm working on is getting robots to tidy the house.
  21. How do you go about doing that?
  22. Well, what you can do is have the robot watch you demonstrate the task, and learn from that.
  23. The robot can then watch what objects you pick up and where to put them,
  24. and try to do the same thing even when you aren't there.
  25. For me, one of the reasons I'm excited about this
  26. is the AI or artificial intelligence problem,
  27. building truly intelligent machines which can do just about anything that you or I can do.
  28. Many scientists think the best way to make progress on this
  29. is through learning algorithms called the "neural networks"
  30. which mimick how the human brain works
  31. and I'll teach about that too.
  32. In this class, you'll learn about machine learning and get to implement them yourself.
  33. This class will have homeworks and programming assignments,
  34. and if you successfully complete this class, you'll also get from me a signed Statement of Accomplishments
  35. stating how you did in the class and which you can put in your resumé.
  36. I hope you sign up on our web site and join us this Fall.