Supercomputing and Computation

SHARE

Machine Learning


The ability to produce ultra-scale data far surpasses any current ability to understand it. Coordinated knowledge discovery across disparate, diverse and dynamic data at scale is becoming extremely difficult. ORNL researchers and member of the Computational Data Analytics group are deriving and implementing predictive algorithms that can learn processes and extract behaviors from data by leveraging the power of ultra-scale computing platforms towards knowledge discovery.

Related Projects

1-2 of 2 Results
 

Ultrascale Predictive Analysis Toolbox
— Supercomputing’s major successes to date have come from discovery through simulation rather than discovery through analysis. Traditional multivariate analysis is not scalable to extremes; high-dimensional data are broken into subsets that ignore system-level context. Can we tractably analyze ultrascale complex-systems data, learning from the system-wide interactions?

Personalized Content Recommendations
— How to detect user interests and automatically recommend interesting contents in a personalized way.

 
 
ASK ORNL

We're always happy to get feedback from our users. Please use the Comments form to send us your comments, questions, and observations.