Bookmark and Share

"At the Edge of AI At the Edge: Ultra-efficient AI on Low-power Compute Platforms," a Presentation from

Mohammad Rastegari, CTO of, presents the "At the Edge of AI At the Edge: Ultra-efficient AI on Low-power Compute Platforms" tutorial at the May 2018 Embedded Vision Summit.

Improvements in deep learning models have increased the demand for AI in several domains. These models demand massive amounts of computation and memory, so current AI applications have to resort to cloud-based solutions. However, AI applications cannot scale via cloud solutions, and sending data over the cloud is not always desired for many reasons (e.g. privacy, bandwidth, ...). Therefore, there is a significant demand for running AI models on edge devices. These devices often have limited compute and memory capacity, so porting deep learning algorithms to these platforms is extremely challenging.

In this presentation, Rastegari introduces’s optimized software platforms, which enable deploying AI models on a variety of low-power compute platforms with extreme resource constraints. The company's solution is rooted in the efficient design of deep neural networks using binary operations and network compression, along with optimization algorithms for training.

Last seen: 10 weeks 2 days ago
Level 1: Prestidigitator
Joined: 2014-10-26
Points: 1

Great talk, very informative, thank you!

I thought you would find the following two links super interesting as they talk about the world's first AI Edge Cameras utilising the ultra low-power super high-performance Myriad X VPUs by Intel.

The first blog gives a step-by-step guide on how to build your own Raspberry Pi 3B+ AI edge camera using two Intel Neural Compute Sticks (NCS2) and runs off PoE.

The other blog talks about Up Square based AI Edge camera utilising 2x NCS2, then MyriadX on mini PCIe and also CPU and GPU simultaneously to run multiple models in real time and on the edge.

Get in touch if you would like to get more info or would like to colaborate on productising these.

Kind Regards,
Martin Peniak, Phd
Head of Innovation | Cortexica Vision Systems