|
|
发表于 2020-9-10 08:06
来自手机
|显示全部楼层
此文章由 Anna_Chen999 原创或转贴，不代表本站立场和观点，版权归 oursteps.com.au 和作者 Anna_Chen999 所有！转贴必须注明作者、出处和本声明，并保持内容完整
本帖最后由 Anna_Chen999 于 2020-9-10 08:10 编辑
BRN前途无量
BrainChip Holdings Ltd. (ASX: BRN), a leading provider of ultra-low power high performance AI technology, today announced its participation at the 2020 Embedded Vision Summit Virtual Conference taking place September 15 –25, 2020 on Tuesdays and Thursdays from 9 a.m. – 2 p.m. PDT. BrainChip will exhibit Akida™, the Company’s next generation artificial intelligence AI Edge device, on September 15th and 17th from 10:30 a.m. to 1:00 p.m. PDT. The ultra-low power, event domain neural processor is capable of inference and incremental learning to support many of today’s standard neural networks.
The company will be running multiple demonstrations of its Akida Neural Processor SoC (NSoC), a revolutionary advanced neural networking processor that brings artificial intelligence to the edge in a way that existing technologies are not capable. The solution is high-performance, small, ultra-low power and enables a wide array of edge capabilities. The Akida NSoC represents a revolutionary new breed of Neural Processing computing devices for Edge AI devices and systems. Comparisons to leading DNN accelerator devices show significantly better images/second/watt running industry standard benchmarks with MobileNet, MobileNet-SSD and Key Word Spotting, while maintaining excellent accuracy.
The Akida NSoC is designed for use as a stand-alone embedded accelerator or as a co-processor. It includes interfaces for ADAS sensors, audio sensors, and other IoT sensors. It also has high-speed data interfaces such as PCI-Express, USB, 12S and 13C. An on-chip MPU is used to control the configuration of the Akida Neuron Fabric as well as off-chip communication of metadata. The Akida NSoC represents a scalable solution utilizing a built-in serial chip to chip connectivity to allow up to 64 devices to be arrayed for a single solution. |
|
参加活动 － 中秋家宴 (2010-9-25) purplenight 
