Where: Exhibit Hall ET 1
Date: Day 2
Start Time: 1:35 pm
End Time: 2:05 pm
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, we will explore the architectural concepts underlying these diverse processors and analyze their suitability for various applications. We will derive the performance bounds of each architecture approach and provide insights on the practical deployment of machine learning using these specialized architectures. In addition, using a case study we will explore the opportunities enabled through designing neural networks to exploit specialized processor architectures.
