The press release could have used a real life example, like "Training MNIST data... | Hacker News

Hacker Newsnew | past | comments | ask | show | jobs | submit

		tiborsaas on Sept 20, 2019 \| parent \| context \| favorite \| on: The BeagleBone AI is Available The press release could have used a real life example, like "Training MNIST dataset takes .5 seconds" or something. Where can I find info about how these edge computing boards are speeding up training time? Or how they compare to a 1080i?

chunsj on Sept 20, 2019 | [–]

As most of the so called machine learning boards, this one is not for learning, just for inferencing at best.

monocasa on Sept 20, 2019 | [–]

I don't think these are meant for training, but instead inference.

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact