Stanford machine learning course

For those of you interested in learning more about machine learning, here’s an interesting opportunity. Andrew Ng at Stanford is offering his annual machine learning class in an online, open access format: Machine Learning. Interested folks will be able to sign up online, watch video lectures and notes, and get feedback on their progress. The class runs October 10th to December 16th, and will touch on most of machine learning’s greatest hits. For people who are interested in getting a firmer grip on the basics of machine learning for their own research, it’d definitely be a worthwhile effort.

2 thoughts on “Stanford machine learning course

  1. Joe Pater

    Sounds great! Coincidentally, Jim White, a student in my LSA course this summer, pointed us towards Andrew Ng’s discussion of L1 and L2 priors for regularization of Maximum Entropy/Log-Linear models – see below for a quote from his post. This is from my course blog, which could have some other useful stuff for people working with weighted constraint models of various types:

    https://blogs.umass.edu/hgcourse/

    I’ve heard that there is a site somewhere that has slides from many of the LSA courses this summer, which may well be of interest to readers of this blog since there were a lot of experimental and computational courses. I’ll post it if I find it, though I’d be happy to be beaten to it…

    \Andrew Ng’s widely cited short paper about L1 vs L2 regularization:

    http://citeseer.ist.psu.edu/viewdoc/summary?doi=10.1.1.81.145

    It’s also available as slides from the associated talk:

    http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.92.9860\

    Reply

Leave a Reply

Your email address will not be published. Required fields are marked *

You may use these HTML tags and attributes: <a href="" title=""> <abbr title=""> <acronym title=""> <b> <blockquote cite=""> <cite> <code> <del datetime=""> <em> <i> <q cite=""> <strike> <strong>