February 22, 2018 - 9.00am GMT
March 15, 2018 - 9.00am GMT
On-device machine learning (ML) processing is already happening in more than 4 billion smart phones. As the adoption of connected devices continues to grow exponentially, the resulting data explosion means cloud processing could soon become an expensive and high-latency luxury.
The Arm ML processor is defining the future of ML inference at the edge, allowing smart devices to make independent decisions based on local data. Developers can easily meet the requirements of tomorrow’s use cases while creating today’s optimal user experience through a combination of power, efficiency and flexibility.
This white paper examines the processor’s optimized design, and how it achieves a massive uplift in efficiency compared to CPUs, GPUs and DSPs.