Edge Computing at Chick-fil-A

Re:Edge Computing at Chick-fil-A by TickleSteve on Wednesday August 22, 2018 @06:14PM (#17822716)

ML implies lots of training data. That gets done centrally as it would need to be done in aggregate.

You don't have low-latency training of a model and use that same model in real-time.

And in your example (admittedly small scale) 12 items of data an hour is not exactly high-data-rate, not enough to justify racks of machines.

[ Parent | on HN ]

Re:Edge Computing at Chick-fil-A by coffeesn0b on Wednesday August 22, 2018 @07:35PM (#17823218)

You’re correct, training is centralized but the devices that use it to function are operated at the edge.

[ Parent | on HN ]

Re:Edge Computing at Chick-fil-A by TickleSteve on Thursday August 23, 2018 @01:01AM (#17824733)

Of course, thats how ML works, central training of a model with use of that model at the edges.

So how often do you distribute a new model for controlling fries?

[ Parent | on HN ]