Live Events

Machine Learning for the Edge – Model Compression and Deployment

Start Time End Time
4 Oct 2022, 04:00 EDT 4 Oct 2022, 05:00 EDT

Overview

AI is no longer limited to powerful computing environments such as GPUs or high-end CPUs and is often integrated into systems with limited resources like patient monitoring, diagnostic systems in vehicles, and manufacturing equipment. Fitting AI onto hardware with limited memory and power supply requires deliberate trade-offs between size of model, accuracy, inference speed, and power consumption — and that process is still challenging in many frameworks for AI development.

With MATLAB and Simulink you can leverage the well-established model-based design workflow to bring your AI models to any edge device, taking advantage of automated code generation, datatype optimization and more.

Highlights

We will show a typical workflow for deploying AI models to edge devices:

  • Model Selection: Identify less complex models and neural networks that still achieve the required accuracy
  • Size Reduction: Tune the hyperparameters and select appropriate datatypes to generate a more compact model
  • Hardware-in-the-loop Tests: Validate the correctness, memory requirements and runtime performance of your models directly on the hardware

About the Presenters

Christoph Stockhammer holds a M.Sc. degree in Mathematics from the Technical University Munich with an emphasis on optimization.

He joined The Mathworks in 2012 and works as an application engineer. His focus areas include Mathematics and data analytics, Machine & Deep Learning as well as the integration of MATLAB software components in other programming languages and environments.

Christoph Kammer is an application engineer at MathWorks Switzerland. He supports customers in many different industries in the areas of machine and deep learning, image and signal processing and deployment to embedded or enterprise systems. Christoph has a master’s degree in Mechanical Engineering from ETHZ and a PhD in Electrical Engineering from EPFL, where he specialized in control design and the control and modelling of electromechanical systems and power systems.

Product Focus

To continue, please disable browser ad blocking for mathworks.com and reload this page.

You are already signed in to your MathWorks Account. Please press the "Submit" button to complete the process.