Shared publicly  - 
Sibyl: A System for Large Scale Machine Learning at Google

Last week, at the IEEE/IFIP International Conference on Dependable Systems and Networks (DSN,, Google Software Engineer +Tushar Chandra gave a keynote address outlining the systems aspects of Sibyl, a supervised machine learning system that is used for solving a variety of prediction challenges, such as YouTube video recommendations.

To learn how Sibyl is being used at Google to solve internet-scale problems while using reasonable resources, watch the video below.
John  Bobir's profile photoGary Guo's profile photoJagat Singh's profile photoZhengbing Li's profile photo
+Research at Google - Bonus points for naming the artificial intelligence system after a famous multiple personality of fiction. =^-^=
Will burn did you hear that
+Tushar Chandra Foreshadowing with humor :) With all of the AI projects at Google, they'll come together as multiple "personalities" from very different domains at some point.
How to train data arrives continuously?Use data in a period(one day,two days....) and old model to get a new model?
Add a comment...