Bookmark and Share

"Emerging Processor Architectures for Deep Learning: Options and Trade-offs," a Presentation from Hailo

Register or sign in to access the Embedded Vision Academy's free technical training content.

The training materials provided by the Embedded Vision Academy are offered free of charge to everyone. All we ask in return is that you register, and tell us a little about yourself so that we can understand a bit about our audience. As detailed in our Privacy Policy, we will not share your registration information, nor contact you, except with your consent.

Registration is free and takes less than one minute. Click here to register, and get full access to the Embedded Vision Academy's unique technical training content.

If you've already registered, click here to sign in.

See a sample of this page's content below:


Orr Danon, CEO of Hailo, presents the "Emerging Processor Architectures for Deep Learning: Options and Trade-offs" tutorial at the May 2019 Embedded Vision Summit.

In the past year, numerous new processor architectures for machine learning have emerged. Many of these focus on edge applications, reflecting the growing demand for deploying machine learning outside of data centers. This intensive focus on processor architecture innovation comes at a perfect time in light of the slowing progress in silicon fabrication technology and the massive opportunities for deployment of AI applications using vision and other sensors.

In this presentation, Danon explores the architectural concepts underlying these diverse processors and analyzes their suitability for various applications. He derives the performance bounds of each architecture approach and provides insights on the practical deployment of machine learning using these specialized architectures. In addition, using a case study, he explores the opportunities enabled through designing neural networks to exploit specialized processor architectures.