www.design-reuse-embedded.com
Find Top SoC Solutions
for AI, Automotive, IoT, Security, Audio & Video...

Taking Constrained ML to the Next Level

community.arm.com, Aug. 06, 2019 – 

The Arm ML Research Lab explores cutting edge techniques and state-of-the-art algorithms. One of our primary research thrusts is investigating ways to bring more machine learning applications to Arm's products, and make existing applications more efficient. Machine learning algorithms, and neural networks (NNs) in particular, are increasingly deployed in very constrained devices. Popular applications include visual and speech interfaces in smart-home devices, predictive maintenance for commercial and industrial machines, and health monitoring in wearable devices. However, due to the energy, power, storage, and compute limitations of these devices, they are frequently limited to simplistic tasks, while more sophisticated requests are off-loaded to a more capable device or to a server. Frequently, even off-loading is not practical due to the additional latency and energy costs, crippling the intelligence available in constrained devices.

However, two of our projects at Arm have significantly advanced the state of the art in dramatically reducing the complexity and size of neural networks, bringing us closer to successfully running more complex tasks on such applications.

Click here to read more...

 Back

Partner with us

List your Products

Suppliers, list and add your products for free.

More about D&R Privacy Policy

© 2024 Design And Reuse

All Rights Reserved.

No portion of this site may be copied, retransmitted, reposted, duplicated or otherwise used without the express written permission of Design And Reuse.