Microsoft squeezed machine learning onto a Raspberry Pi
Artificial Intelligence and Machine Learning usually work best with a lot of horsepower behind them to crunch the data, compute possibilities and instantly come up with better solutions.
That's why most AI systems rely on local sensors to gather input, while more powerful hardware in the cloud manages all the heavy lifting of output. It's how Apple's Siri and Amazon Alexa work, and how IBM Watson can tackle virtually any major task. It is, though, a limiting approach when it comes to making smarter Internet of Things and applying intelligence when there isn't Internet connectivity.
SEE ALSO:Scientists are creating drones that fly in sync with each other“The dominant paradigm is that these [sensor] devices are dumb,” said senior researcher with Microsoft Research India, Manik Varma.
Now, Varma's team in India and Microsoft researchers in Redmond, Washington, (the entire project is led by lead researcher Ofer Dekel) have figured out how to compress neural networks, the synapses of Machine Learning, down from 32 bits to, sometimes, a single bit and run them on a $10 Raspberry Pi, a low-powered, credit-card-sized computer with a handful of ports and no screen. It's really just an open-source motherboard that can be deployed anywhere. The company announced the research in a blog post on Thursday.
Microsoft's work is part of a growing trend of moving Machine Learning closer to devices and end users.
Earlier this month at is annual World Wide Developer's Conference, Apple announced new Machine Learning APIs (Vision and Natural Language) that allow developers to add machine learning-based intelligence to their apps with just a couple of lines of code. They also unveiled Core ML for developers more well-versed in AI to take full advantage of all inference capabilities available on the local hardware. Apple's model does have the developers train their Machine Learning algorithms on libraries Apple provides. The system then converts the code to run the AI locally.
Obviously, in Apple's case, that hardware is inside a $700 iPhone and the CPU is much, much more powerful than anything found on a Raspberry Pi. Still, the trend is clear. These companies are moving intelligence closer to the local hardware and, where possible, relying less on constant access to massive data and intelligence stores in the cloud.
“If you’re driving on a highway and there isn’t connectivity there, you don’t want the [AI] implant to stop working,” said Varma in the blog post. “In fact, that’s where you really need it the most.”
It's an approach that will make sense for smaller, sensor-based tasks that can learn by location, intention, recent action and the device data. In the near term, it won't be a solution for, say, coming up with new cancer therapies (one of the areas of interest for IBM's Watson AI).
As for Microsoft, this Raspberry Pi breakthrough is simply phase one in a quest to compress neural networks so much that they can run on a breadcrumb-sized micro controller. To get there, the machine learning models need to be, according to Microsoft, as much as 10,000 times smaller. That's a problem the team is still working on.
In the meantime, Microsoft released previews of the Raspberry Pi-sized machine learning and training algorithms on GitHub where enterprising developers can try them out and, potentially deploy on Raspberry Pi 3 and Raspberry Pi Zero.
Ultimately, this is another piece of Microsoft's growing Intelligent Edge strategy, which Microsoft CEO Satya Nadella outlined earlier this year a Microsoft Build developers conference. Microsoft hopes to see these tiny AI-able microprocessors deployed in everything from our offices to the clothes we wear.
For Varma, who is visually impaired, the research is a little more personal. His team is already developing a prototype intelligent walking stick to showcase their research.
Related Video: Robots are taking over the Museum of Industry and Science in Chicago
(责任编辑:资讯)
- 优化广东优质农产品产销资源对接!“农友圈”又有新动作
- [Herald Interview] Moon vows all
- Finally, the feminine urge is taking over Twitter
- [Profile] Friend of ex
- If aliens harnessed solar power, could we detect them? NASA investigated.
- Amazon Android Days sale 2024: Save on unlocked phones, tablets, and more
- Apple launches 16
- Let's face it: Flying cars are never going to be a thing
- Steve Buscemi dresses up as his own meme, immediately wins Halloween
- Best smart home deals this week at Amazon
- TikTok wants you to stop dressing for the male gaze
- 没区别 没亮点 没创意
- US fully implements travel ban on North Korea
-
Military prosecutors indict intel official over leaking 'black agent' info
(Getty Images Bank)The defense ministry's prosecutors' office on Tuesday indicted a milita ...[详细] -
Rodrygo sends Real second in La Liga
SEVILLE:Rodrygo hit a brace to earn Real Madrid a 2-1 win over Sevilla in La Liga on Saturday, sendi ...[详细] -
Jacobs' back issue delays Kerley 100m 'challenge'
ROME:Olympic 100m champion Marcell Jacobs will sit out this weekend's highly-anticipated sprint ...[详细] -
North Korea's new ICBM test 'successful': defense ministry
South Korea's defense ministry on Friday characterized North Korea's projectile, fired earlier this ...[详细] -
Where to pre-order the Pixel 9 and Pixel 9 ProGoogleGoogle Pixel 9Starting at $799 (plus get a free ...[详细]
-
刘绪敏在《天下达人秀》上用“龙行十八式”为观察员倒茶雅安日报讯7日晚9时30分,浙江卫视《天下达人秀》选秀节目与全国观众见面。节目中,我市茶艺师刘绪敏登场,用一把长嘴茶壶演绎“龙行十八式”,争夺当晚达 ...[详细]
-
Apple's new iOS update fixes dreaded multitasking bug
There's nothing as annoying as the iPhone shutting down your background apps while you're working on ...[详细] -
过往车辆正有序通过滑坡地段雅安日报讯昨(11)日早上8点整,雅(安)上(里)线十公桩滑坡段抢通,车辆可正式通行,比前期预计的抢通时间提前了两天。7月5日至6日,受强降雨影响,雅上线十公桩处连续两次出现 ...[详细]
-
By the time I tapped out of Persona 5after 60 hours of a massive high school adventure that I was en ...[详细]
-
播放量破6千万!潮州橄榄抖音大火_南方+_南方plus点击图片查看专题报道线下橄榄结硕果,线上橄榄惹人馋。随着潮州橄榄集中上市,今年9月份上线的抖音话题#潮州橄榄 收获众多投稿,话题播放量6095.5 ...[详细]
Washington Mystics vs. Chicago Sky 2024 livestream: Watch live WNBA
Moon, Trump agree to bring N. Korea to dialogue table through sanctions, pressure
- 一针一线串起两代人的传承故事
- 没区别 没亮点 没创意
- Sheryl Sandberg discussed 'Facebook lite' for kids in 2013, leaked messages show
- Uber's new self
- Korea's economy to stop growing without drastic labor change: FKI
- Please enjoy Obama photographer Pete Souza's latest flawless Trump troll
- Chinese hackers infect carriers to steal SMS messages