Internet of Things tagged posts

Chip Could bring Deep Learning to Mobile Devices

MIT researchers have designed a new chip to implement neural networks. It is 10 times as efficient as a mobile GPU, so it could enable mobile devices to run powerful artificial-intelligence algorithms locally, rather than uploading data to the Internet for processing. Credit: MIT News

MIT researchers have designed a new chip to implement neural networks. It is 10 times as efficient as a mobile GPU, so it could enable mobile devices to run powerful artificial-intelligence algorithms locally, rather than uploading data to the Internet for processing. Credit: MIT News

Advance could enable mobile devices to implement ‘neural networks’ modeled on the human brain. It is 10 times as efficient as a mobile GPU, so it could enable mobile devices to run powerful artificial-intelligence algorithms locally, rather than uploading data to the Internet for processing.

Neural networks are typically implemented using graphics processing units (GPUs), special-purpose graphics chips found in all computing devices with screens...

Read More

Powering the Next billion Devices with Wi-Fi

The UW team used ambient signals from this Wi-Fi router to power sensors in a low-resolution camera and other devices. Credit: Dennis Wise/University of Washington

The UW team used ambient signals from this Wi-Fi router to power sensors in a low-resolution camera and other devices. Credit: Dennis Wise/University of Washington

UW engineers have developed a novel technology that uses a Wi-Fi router – a source of ubiquitous but untapped energy in indoor environments – to power devices. The Power Over Wi-Fi (PoWiFi) system is one of the most innovative and game-changing technologies of the year, according to Popular Science, which included it in the magazine’s annual “Best of What’s New” awards announced Wednesday.

Researchers earlier this year show how they harvested energy fr to further improve the efficiency of the system to enable operation at larger distances and power numerous more sensors and applications,” said co-author Shyam Gollakota, assistan...

Read More