Chicago Machine Learning Study Group Message Board › Machine Learning Resources

Machine Learning Resources

Rob L.
RobLancaster
Group Organizer
Chicago, IL
Post #: 2
Here are a few books we talked about last night for those interested:

Algorithms of the Intelligent Web This is a really accessible book for those getting started in applying ML methods. This book has great examples plus source code (in Java). The book gives a decent, easily digestible overview of many methods. Math & theory are pretty light in this book, which is good for practitioners just starting out.

Programming Collective Intelligence This is a book I have, though haven't started reading. I believe Don recommended this one last night. From what I've been told this is another great book for applying ML to various problems and includes source code (in Python). Don characterized the "Algorithms" book as a java port of this one.

Data Mining: Practical Machine Learning Tools and Techniques This book is much heavier on theory and math than the previous two titles. Although more dense than the above two titles, you won't need an advanced stats degree to follow it. I'd highly recommend this as a followup to one of the above as a way to get greater insight machine learning. The authors of this book are also the creaters of Weka which is pretty easy to use software with a large number of built-in ML techniques.
Duane J.
user 12526883
Salt Lake City, UT
Post #: 4
Thanks Rob! I'm glad you were able to share your personal take on these books, especially since there are so many out there. Algorithms of the Intelligent Web sounds quite interesting and approachable.
Bruce P.
user 9567325
Chicago, IL
Post #: 8
Hi All,

At least one of these titles I could download in an accessible format. More suggestions would help greatly. Also, classes you've liked, school and course number, would help me ferret out some other textbooks in accessible formats.

Thanks,
bcp
Rob L.
RobLancaster
Group Organizer
Chicago, IL
Post #: 3
Here are a few more resources:

This is a very good lecture series:
Stanford Machine Learning Course

Code resources:
Weka: Console and java api with various ML classification, clustering techniques, etc.
Mahout: Apache scalable machine learning library for use with Hadoop.
Rob L.
RobLancaster
Group Organizer
Chicago, IL
Post #: 5
Konrad turned us on to this lecture series at the end of yesterday's talk:


Cognitive Science and Machine Learning Summer School 2010 - Sardinia
A former member
Post #: 1
A few more recommended books:

Bishop, "Pattern Recognition and Machine Learning". Bishop is of the Bayesian school of thought. His book on neural nets was one of the best back when NNs were a technique du jour.

MacKay, "Information Theory, Inference, and Learning Algorithms". Written with a good sense of humor (just check out the author's comparison to Harry Potter at the next link), this is another Bayesian book that adds information theory elements. These are important when reasoning about probability priors. It is freely available in electronic form.

Another classic text by several giants in the area, although light on Bayesian techniques specifically, is "The Elements of Statistical Learning". A older but still quite recent edition is freely available in electronic form.

Finally, if you are specifically interested in why Bayesian view "just makes sense" compared to 'orthodox' statistics as it is still being taught and how someone like a physicist would convert to Bayesianism from first principles, I'd recommend this undeservedly less-well-known gem of a book: "Data Analysis: A Bayesian Tutorial".

Powered by mvnForum

Our Sponsors

People in this
Meetup are also in:

Sign up

Meetup members, Log in

By clicking "Sign up" or "Sign up using Facebook", you confirm that you accept our Terms of Service & Privacy Policy