Message Boards

24533 Views

7 Replies

13 Total Likes

View groups...

Follow this post

Share this post:

GROUPS:

Staff Picks Data Science Physics Wolfram Language Machine Learning Know-How Neural Networks Artificial Intelligence

Higgs Boson Classification via Neural Network

Posted 8 years ago

POSTED BY: Arnoud Buzing

7 Replies

Sort By:

Posted 7 years ago

It's quite old, as is my desktop system: a GeForce GTX 650 Ti. I am currently shopping for a new desktop system. If I actually go for a full-blown GPU co-processor card (in addition to one for the video display), any recommendations?

POSTED BY: Alan Lewis

Posted 7 years ago

Arnoud, Thank you! I actually didn't realize I could use my existing NVIDIA video card for this. But now (after a driver update) I see I can.

POSTED BY: Alan Lewis

Posted 7 years ago

Good to hear! Keeping drivers up to date is always a good thing, especially with graphics drivers. Just to satisfy my curiosity, what nVidia card do you have?

POSTED BY: Arnoud Buzing

Posted 7 years ago

Excellent post. I see you are using TargetDevice->"GPU". I am shopping for a new desktop and thinking about getting one with a GPU. Can you discuss the run-time improvement associated with this problem and the GPU, and give as much detail about your hardware and operating system environment as you care to share.

POSTED BY: Alan Lewis

Posted 7 years ago

Alan, I use an NVIDIA GeForce GTX 1080 card: Speedups differ a lot for different training scenarios. For this example I am seeing about 2x speedup. The LeNet example in the NetTrain reference documentation shows a 10x speed-up, and the CIFAR-10 example is about 60x for me.