Photo: Tekla Perry Teal's drone uses the Nvidia Jetson module to identify what its cameras see<\/p>\n
People arejust now getting comfortable with the ideathat data from many electronic gadgets they use flies up to the cloud. But going forward, much of that data will stick closer to Earth, processed in hardware that lives at the so-called edgefor example, inside security cameras or drones. <\/p>\n
Thats why Nvidia, the processor company whose graphics processing units (GPUs) are powering much of the boom in deep learning, is now focused on the edge. Deepu Talla, vice president and general manager of the companys Tegra businessunit, says bringing AI technology to the edge will make a new class of intelligent machines possible. These devices will enable intelligent video analytics that keep our cities smarter and safer, new kinds of robots that optimize manufacturing, and new collaboration that makes long-distance work more efficient, he said in a statement. <\/p>\n
Why the move to the edge? At a press event held Tuesday in San Francisco, Talla gave four main reasons: bandwidth, latency, privacy, and availability. Bandwidth is becoming an issue for cloud processing, he indicated, particularly for video, because cameras in video applications such aspublic safety are moving to 4K resolution and increasing in numbers. By 2020, there will be 1 billion cameras in the world doing public safety and streaming data, he said. Theres not enough upstream bandwidth available to send all this to the cloud. So, processing at the edge will be an absolute necessity. <\/p>\n
Latency, he said, becomes an issue in robotics and self-driving cars, applications in which decisions have to be made with lightning speed. Privacy, of course, is easier to protect when data isnt moving around. And availability of the cloud, Talla pointed out, is an issue in many parts of the world where communications are limited. <\/p>\n
We will see AI transferring to the edge, he said, with future intelligent applications using a combination of edge and cloud processing. <\/p>\n
Nvidia, of course, wasnt painting this glowing picture of edge computing without some self-interest. At the event, the company announced its new edge-processing platform, the Nvidia Jetson TX2. This credit cardsizemodule is a plug-in replacement for the companys Jetson TX1, designed for embedded computing. Depending on how it is applied, it can either run at twice the speed of its predecessor or use half the power. Detailed specs are here. The developer kit costs $600, $300 for educators; the production version will sell for $400. <\/p>\n
Developers, showing off their work at the launch event, were happy to point out how they are using or intend to use internal AI processing at the edge. A few examples: <\/p>\n
IEEE Spectrums blog featuring the people, places, and passions of the world of technologists in Silicon Valley and its environs. Contact us:t.perry@ieee.org <\/p>\n<\/p>\n
University of Michigan \"micromotes\" aim to make the Internet of Things smarter without consuming more power 10Feb <\/p>\n<\/p>\n
Inventors of the CCD, the pinned photodiode, and the CMOS imager honored with 1 million prize 2Feb <\/p>\n<\/p>\n
Ubers experiment in San Francisco showed that bicycles and bike lanes are a problem self-driving cars are struggling to crack 31Jan <\/p>\n<\/p>\n
Nvidia CEO Jen-Hsun Huang wants his robocar computer package to become an industry standard 5Jan <\/p>\n<\/p>\n
Supercharged hardware will speed up deep learning in everything from tiny devices to massivedatacenters 29Dec2016 <\/p>\n<\/p>\n
Microchips AWS-ECC508 bakes in securecommunications 22Dec2016 <\/p>\n<\/p>\n
Giving each pixel hundreds of memory cells means CMOS imaging chips will have much faster global shutter speed 16Dec2016 <\/p>\n<\/p>\n
Danish island experiments with demand aggregation 7Dec2016 <\/p>\n<\/p>\n
The company will expand the autonomous-taxi experiment it began some months ago in Singapore 21Nov2016 <\/p>\n<\/p>\n
Seeing isnt just about taking pictures. The real revolution will come when our digital devices understand whats in front of their eyes 3Nov2016 <\/p>\n<\/p>\n
The \"Jeep hacker\" says denial-of-service attacks against cars are easy hacksand urges people not to buy any car dongles 28Oct2016 <\/p>\n<\/p>\n
AI-powered traffic light coordination would cut time spent in the car, traffic congestion, and emissions 17Oct2016 <\/p>\n<\/p>\n
Self-driving cars require driver-monitoring capability to know when it is safe to hand over control 4Oct2016 <\/p>\n<\/p>\n
A revised draft of regulations proposes doing away with drivers during tests 3Oct2016 <\/p>\n<\/p>\n
If your smart glasses contain a virtual companion who knows exactly what you are doing and has an opinion about it, are you living in an augmented reality? 30Sep2016 <\/p>\n<\/p>\n
Hondas new Acura NSX is the first to marry a V-6 engine to three electric motors for high-speed steering 26Sep2016 <\/p>\n<\/p>\n
A squishy underwater robot with limbs that bend in every direction requires unusual control strategies 15Aug2016 <\/p>\n<\/p>\n
Industry leaders from around the globe use multiphysics simulation to stay ahead of the curve <\/p>\n<\/p>\n
Applications streamline capacitive touchscreen design and optimize the workflow <\/p>\n<\/p>\n
Hear from simulation experts about their experience with computational apps and how they are creating the future of numerical simulation <\/p>\n
<\/p>\n
Here is the original post: <\/p>\n
Nvidia wants AI to Get Out of the Cloud and Into a Camera, Drone, or Other Gadget Near You - IEEE Spectrum<\/a><\/p>\n","protected":false},"excerpt":{"rendered":" Photo: Tekla Perry Teal's drone uses the Nvidia Jetson module to identify what its cameras see People arejust now getting comfortable with the ideathat data from many electronic gadgets they use flies up to the cloud. Continue reading