Real-World Machine Learning on Big Data: Which Method(s) Should You Use?

Data Science Ballroom AB
Average rating: ***..
(3.30, 10 ratings)

Suppose you have a real-world big data problem before you, and you want to use machine learning (ML) to solve it. Which ML method(s) should you use? How does the fact that the dataset is big affect your choices? Drawing on two decades of experience in ML on big data, I will highlight a few key principles that can be distilled from the thousands of theoretical and experimental results in the research literature surrounding such questions. These will be illustrated through a handful of real-world ML success stories, where best-in-class results were achieved, including difficult examples in medical diagnosis, direct marketing, financial services, and astronomy.

Photo of Alexander Gray

Alexander Gray

Skytree, Inc.

Dr. Gray obtained degrees in Applied Mathematics and Computer Science from Berkeley and a PhD in Computer Science from Carnegie Mellon, and is a tenured professor at Georgia Tech. His lab works to scale up all of the major practical methods of machine learning (ML) to massive datasets. He began working on this problem at NASA in 1993 (long before the current fashionable talk of “big data”). His large-scale algorithms helped enable the Science journal’s Top Breakthrough of 2003, and have won a number of research awards. He is a member of the National Academy of Sciences (NAS) Committee on the Analysis of Massive Data, is a NAS Kavli Scholar, and frequently gives invited tutorial lectures on massive-scale ML at top research conferences and agencies.

Comments on this page are now closed.

Comments

Minakshi Mukherjee
03/03/2013 4:44pm PST

Hi Dr Gray,

I attended the session and it was very informative. Are you going to post the slides? Thanks Mina

Yuehui Yao
03/02/2013 11:51am PST

Hi -

Can the speaker share the slides for the session? I found the tabled comparison between different types of machine learning models very insightly.

Thank you very much.

Sponsors

Sponsorship Opportunities

For information on exhibition and sponsorship opportunities at the conference, contact Susan Stewart at sstewart@oreilly.com

Media Partner Opportunities

For information on trade opportunities with O'Reilly conferences contact Kathy Yu at mediapartners
@oreilly.com

Press and Media

For media-related inquiries, contact Maureen Jennings at maureen@oreilly.com

Contact Us

View a complete list of Strata contacts