AI processing card is for edge computing
UP Bridge the Gap, a brand of Aaeon Europe, launches AI Core, believed to be the first embedded, compact artificial intelligence (AI) processing cards for edge computing.
AI Core is a mini-PCIe module powered by Intel Movidius Myriad 2 technology. This low-power module enhances industrial IoT edge devices with hardware accelerated deep learning and enhanced machine vision functionality. Aaeon Technology says it is one of the first IPC manufacturers to address the growing need for AI on the edge with dedicated hardware.
Most of the available IoT solutions are focused on connecting edge devices to the cloud. These deployments face challenges related to latency, network bandwidth, reliability and security. Not all the tasks and decision making processes can be addressed in cloud-only models. AI Core overcomes cloud limitations by bringing AI performance and hardware acceleration to be on the edge of the IoT.
AI Core is powered by the Intel Movidius Myriad 2 vision processing unit (VPU). With 512Mbyte onboard DDR memory, this mini card module requires very little energy to enable local deep-learning and computing vision algorithms.
AI Core can be used for object recognition in drones, high-end virtual reality headsets, robotics, smart home devices, smart cameras and video surveillance.
AI Core is a companion board of UP Squared, the compact expandable board powered by Intel Celeron N3350, Intel Pentium N4200, Intel Atom x5-E3940, and Intel Atom x7-E3950 processor families. The mini-PCIe interface makes AI Core compatible with most industrial computer boards in the market, adds Aaeon.
Using the supported software tools, a neural network can be created and trained in the cloud and then run locally on AI Core.
AI Core is compatible with the Intel Movidius Neural Compute Stick software development kit.
AI Core is available for pre-order on UP Shop and will also be available soon at channel and distributor partners of Aaeon and UP. The delivery of AI Core starts in April 2018.