We’ve completed a significant upgrade to our video platform!

Still in development

Let us know what you think. We’d love your feedback.

x

Confirm Download

Simultaneous file downloading works best in FireFox, Chrome, and Safari browsers. Please keep this window open until all downloads are complete. Some customers prefer using download managers like GetThemAll Downloader for Chrome or DownThemAll! for Firefox.

Cancel Download

Hilary Mason: An Introduction to Machine Learning with Web Data

    • Introduction  (Free)

      This introduction explores why machine learning is particularly relevant now and the kinds of applications that are becoming possible with modern mathematical techniques and software libraries.
    • 00:20:25

    • Classifying Web Documents - The Theory  (Free)

      Classification -- that is, identifying a label that applies to an item -- is a classic machine learning task that is very relevant to the messy data that we get from the web. This section explores the mathematical theory behind building a simple classifier.
    • 00:29:23

    • Clustering, Recommendations, and Probability

      Clustering is a classic unsupervised learning problem and is usually the first technique we reach for when using unlabeled data. We'll explore clustering using bookmark data, including clustering an entire dataset. Recommendation systems are a special case of the same problem, so we'll build one of those, too!
    • 00:54:06

    • Conclusion

      This section sums up the math, code, and data projects from the class.
    • 00:11:30

Hilary Mason: An Introduction to Machine Learning with Web Data

  • Publisher: O'Reilly Media
  • Released: May 2011
  • Run time: 2 hours 43 minutes

Once you've accumulated a pile of data through your web application, what do you do with it? In this insightful video course, bit.ly lead scientist Hilary Mason shows you how to solve data analysis problems using basic machine learning techniques and frameworks. You'll follow several examples through the entire process—from obtaining, cleaning, and exploring data to building a model and interpreting the results.

Examine several real-world analysis solutions, including supervised learning and classification, unsupervised learning and clustering, and building common machine learning applications such as recommendation systems. If you're a developer interested in the math and processes necessary to apply machine learning techniques to web data, this video course is for you.

Intended Audience:

This class is intended for developers who are interested in an introduction to the math and processes to apply machine learning techniques to web data.