Lecture 01 – The Learning Problem

The Learning Problem – Introduction; supervised, unsupervised, and reinforcement learning. Components of the learning problem. Lecture 1 of 18 of Caltech’s Machine Learning Course – CS 156 by Professor Yaser Abu-Mostafa. View course materials in iTunes U Course App – and on the course website –

Produced in association with Caltech Academic Media Technologies under the Attribution-NonCommercial-NoDerivs Creative Commons License (CC BY-NC-ND). To learn more about this license,

This lecture was recorded on April 3, 2012, in Hameetman Auditorium at Caltech, Pasadena, CA, USA.

30 comments

  1. Intrepid Mudslinger says:

    who on earth disliked and downvoted this video?..the professor’s teaching from just the first lesson has inspired me to research into other ML ANNs beside just the perceptron like the Hopfield NN and gain a megatonne of info…from just the first damned lesson..and i was simply clicking on recommendations goddamit…had no clue about ML..those damned lucky students

  2. an yu says:

    The professor explains everything so clearly! The video and audio have high quality! The questions asked by the students have high quality!

  3. Shoaib Khan says:

    Seriously, this is the best lecture on #ML available on web. Brilliant explanation and the examples at the beginning (specially the Credit approval one) is well explained and fits exactly into introduction to ML.

  4. Turing Machine says:

    (Don’t read this comment.)

    Stopped at 32:35. What are x, y, mathcal{H} in the movie ratings example? A guess:

    x = (viewer ID, movie ID) in mathcal{R}^2
    y = +1 or -1 depending on whether the rating is good or bad
    h(x) = sign(w(viewer(x)) . t(movie(x)))
    where
    viewer(x) is the first coordinate of x, and movie(x) is the second coordinate of x;
    w returns a viewer’s vector, and t returns a movie’s vector.

  5. Luiz Henrique Lima says:

    One of the best teachers I have ever seen! Congratulations, Professor Mustafa!

  6. Amanì Michael says:

    This lecturer is incredible <3 I wish I could learn from them more directly, and will be looking out for opportunities to do so! Thank you for making this available 🙂

  7. Neil Bryan Closa says:

    This kind of learning resource is useful for providing professionals with the right intuition and conceptual framework in the technology of Machine Learning. More power to California Institute of Technology and Professor Yaser Abu-Mostafa.

Comments are closed.