Slashdot Mirror
New Chip Offers Artificial Intelligence On A USB Stick (pcmag.com)
An anonymous reader writes: "Pretty much any device with a USB port will be able to use advanced neural networks," reports PC Magazine, announcing the new Fathom Neural Compute Stick from chip-maker (and Google supplier) Movidius. "Once it's plugged into a Linux-powered device, it will enable that device to perform neural network functions like language comprehension, image recognition, and pattern detection," and without even using an external power supply.
Device manufacturers could now move AI-level processing from the cloud down to end users, PC Magazine reports, with one New York computer science professor saying the technology means that now "every robot, big and small, can now have state-of-the-art vision capabilities."
The article argues that this standalone, ultra-low power neural network could start the creation of a whole new category of next-generation consumer technologies.
Device manufacturers could now move AI-level processing from the cloud down to end users, PC Magazine reports, with one New York computer science professor saying the technology means that now "every robot, big and small, can now have state-of-the-art vision capabilities."
The article argues that this standalone, ultra-low power neural network could start the creation of a whole new category of next-generation consumer technologies.
We should first create AI before we start selling it on fucking USB sticks.
This is all very interesting. However, there is no indication of when the sticks will become generally available.
There also seems to be very little actual information about it. How much memory does it have? How many FLOPS? The product sheet says it uses 16 bit floats, which are generally good enough for NNs. But can it do FP32 and FP64 at all? The power consumption is ~1W, so I doubt if it can do much with that. The USB interface would be a major bottleneck, as you fed information in, and pulled results out. A GPU on a PCIe bus would be way faster at that ... and nearly all computers already have a GPU. I think I will continue to run my NNs on a Tesla K80.
Fuck off. If you want me to have even a passing interest in this i want to see how easy it will be to use and port applications BEFORE I give you my details.
I suspect (yes, I'm guessing) that this may be somewhat less expensive than a Tesla K80.
Sure, but it is more expensive than the GPU already included in your computer, which has a marginal cost of $0 since you already have it. So why should you buy something that is far slower and less capable than something that is effectively free?
Also, you don't need to buy a Tesla K80. You can rent them by the minute from AWS.