Tying machine learning to physics to support new science | #OpenPOWERSummit
by Nelson Williams | Apr 22, 2016
Big Data is a powerful technology for business, but that power is even more important in the world of science. While business collects data on customers and processes, science can create staggering amounts of information with a single experiment. Often, that data can take years to work through by conventional means. Big Data processing can turn years into months or weeks. One of the latest tools science has taken up to handle their Big Data needs is machine learning.
To gain some insight on recent machine learning programs, David Floyer (@dfloyer), cohost of theCUBE, from the SiliconANGLE Media team, spoke to Brock Palen at the OpenPower Summit 2016 convention. Palen is the director of Advanced Research Computing Technology Services at the University of Michigan.
A new platform
The conversation started as Palen described the system. He said the new platform was called ConFlux and represented a joint project with IBM. Its purpose was to be a platform for data-driven computational physics. The system, he said, was a way to couple machine learning with traditional computational physics.
The physics in question, Palen explained, had to do with modeling events like weather, blood flow, materials combustion and other things. These events, he continued, were very hard to model even with today’s powerful machines. By adding machine learning to large-scale simulation, they could guide and improve existing computational physics.
A vision of data
ConFlux was designed around handling a lot of data. It can access data in several ways, Palen said, so they won’t need to move huge chunks of data around as often. This also reduces the amount of shadow data duplicated in dark corners of the system.
Beyond the immediate benefits, Palen described the vision of ConFlux as a platform of resources to support a diverse group of researchers. Today, they work with several thousand people, but in the future they expect to touch many more. ConFlux is something they hope to build and grow to create the best science they’ve ever had.
@theCUBE
#OpenPOWERSummit
Forgot Password
Almost there!
We just sent you a verification email. Please verify your account to gain access to
OpenPOWER Summit 2016 | San Jose. If you don’t think you received an email check your
spam folder.
In order to sign in, enter the email address you used to registered for the event. Once completed, you will receive an email with a verification link. Open this link to automatically sign into the site.
Register For OpenPOWER Summit 2016 | San Jose
Please fill out the information below. You will recieve an email with a verification link confirming your registration. Click the link to automatically sign into the site.
You’re almost there!
We just sent you a verification email. Please click the verification button in the email. Once your email address is verified, you will have full access to all event content for OpenPOWER Summit 2016 | San Jose.
I want my badge and interests to be visible to all attendees.
Checking this box will display your presense on the attendees list, view your profile and allow other attendees to contact you via 1-1 chat. Read the Privacy Policy. At any time, you can choose to disable this preference.
Select your Interests!
add
Upload your photo
Uploading..
OR
Connect via Twitter
Connect via Linkedin
EDIT PASSWORD
Share
Forgot Password
Almost there!
We just sent you a verification email. Please verify your account to gain access to
OpenPOWER Summit 2016 | San Jose. If you don’t think you received an email check your
spam folder.
In order to sign in, enter the email address you used to registered for the event. Once completed, you will receive an email with a verification link. Open this link to automatically sign into the site.
Sign in to gain access to OpenPOWER Summit 2016 | San Jose
Please sign in with LinkedIn to continue to OpenPOWER Summit 2016 | San Jose. Signing in with LinkedIn ensures a professional environment.
Are you sure you want to remove access rights for this user?
Details
Manage Access
email address
Community Invitation
Brock Palen, University of Michigan | OpenPOWER Summit 2016
Tying machine learning to physics to support new science | #OpenPOWERSummit
by Nelson Williams | Apr 22, 2016
Big Data is a powerful technology for business, but that power is even more important in the world of science. While business collects data on customers and processes, science can create staggering amounts of information with a single experiment. Often, that data can take years to work through by conventional means. Big Data processing can turn years into months or weeks. One of the latest tools science has taken up to handle their Big Data needs is machine learning.
To gain some insight on recent machine learning programs, David Floyer (@dfloyer), cohost of theCUBE, from the SiliconANGLE Media team, spoke to Brock Palen at the OpenPower Summit 2016 convention. Palen is the director of Advanced Research Computing Technology Services at the University of Michigan.
A new platform
The conversation started as Palen described the system. He said the new platform was called ConFlux and represented a joint project with IBM. Its purpose was to be a platform for data-driven computational physics. The system, he said, was a way to couple machine learning with traditional computational physics.
The physics in question, Palen explained, had to do with modeling events like weather, blood flow, materials combustion and other things. These events, he continued, were very hard to model even with today’s powerful machines. By adding machine learning to large-scale simulation, they could guide and improve existing computational physics.
A vision of data
ConFlux was designed around handling a lot of data. It can access data in several ways, Palen said, so they won’t need to move huge chunks of data around as often. This also reduces the amount of shadow data duplicated in dark corners of the system.
Beyond the immediate benefits, Palen described the vision of ConFlux as a platform of resources to support a diverse group of researchers. Today, they work with several thousand people, but in the future they expect to touch many more. ConFlux is something they hope to build and grow to create the best science they’ve ever had.
@theCUBE
#OpenPOWERSummit
