Systems & Design

Optimizing Deep-Learning Inference For Embedded Devices

Challenges in deploying artificial neural networks.


Deep artificial neural networks (ANNs) have emerged as universal feature extractors in various tasks as they approach (and in many cases surpass) human-level performance. They have become fundamental building blocks of almost every modern artificially intelligent (AI) application, from online shop recommendations to self-driving cars.

This whitepaper highlights how different challenges related to the deployment (inference) of artificial neural networks (ANNs) on embedded devices can be addressed. For this, the state-of-the-art object detection single-shot detector (SSD) is optimized for execution on the Nvidia Jetson X2 and Drive PX2 platforms. In the following, deep neural networks and the challenges related to training and inference are introduced.

To read more, click here.

Leave a Reply

(Note: This name will be displayed publicly)