Deploying Deep Learning Models on Embedded Processors for Autonomous Systems with MATLAB

Wednesday, May 22, 1:35 PM - 2:05 PM
Summit Track: 
Enabling Technologies
Exhibit Hall ET 2

Learn how to bring the power of deep neural networks to memory- and power-constrained devices like those used in robotics and automated driving. The workflow starts with an algorithm design in MATLAB, which enjoys universal appeal among engineers and scientists because of its expressive power and ease of use. The algorithm may employ deep learning networks augmented with traditional computer vision techniques and can be tested and verified within MATLAB. Next, the networks are trained using MATLAB's GPU and parallel computing support either on the desktop, a local compute cluster, or in the cloud. In the deployment phase, code generation tools are employed to automatically generate optimized code that can target both embedded GPUs like Jetson, Jetson Drive AGX Xavier, Intel-based CPU platforms or ARM-based embedded platforms. The generated code leverages target-specific libraries that are highly optimized for the target architecture and memory model.


Bill Chou

Sr. Product Marketing Manager, MathWorks

Bill Chou is the product manager for MATLAB Coder and GPU Coder at MathWorks. He has worked with MATLAB and Simulink customers deploying algorithms to embedded systems for the past 13 years. Bill holds a Master’s degree in Electrical Engineering from the University of Southern California focusing on image and video processing.

Sandeep Hiremath

Product Manager, MathWorks

Sandeep Hiremath is the embedded vision product manager at MathWorks with over 10 years of experience in system design and embedded hardware deployment. Prior to being a product manager, as a technology evangelist at MathWorks, he enabled users in academia to successfully develop and implement autonomous and robotic applications. Sandeep has a Master's in mechanical engineering from Clemson University specializing in autonomous control and design of wearable sensors and actuators.

See you at the Summit! May 18-21 in Santa Clara, California!