MATLAB and PyTorch: from Co-execution to Deployment

PyTorch and TensorFlow are widely used to develop AI models that engineers incorporate into existing system designs as part of their AI enhancement strategies. MATLAB and Simulink integrate with PyTorch and TensorFlow to enable a range of capabilities including domain-specific data preprocessing, system-level simulation of AI models with pre and postprocessing, interpretability and robustness verification of the AI models, AI model compression for implementation, and C/C++/CUDA code generation.

In this webinar, we will explore various options and advantages of integrating PyTorch and TensorFlow with MATLAB and Simulink, illustrating each with practical examples. Key integration approaches include:

• Co-execution of PyTorch models within MATLAB and Simulink for system-level simulation
• Automatic C/C++/CUDA code generation from PyTorch models for deployment to prototyping and production hardware
• Formal verification of PyTorch models to ensure reliability and safety
• Model conversion between MATLAB, PyTorch, and TensorFlow to streamline workflows and leverage the strengths of each platform

Please allow approximately 45 minutes to attend the presentation and Q&A session. We will be recording this webinar, so if you can't make it for the live broadcast, register and we will send you a link to watch it on-demand.

About the Presenters

Bill Chou has focused on code generation technologies at MathWorks for over 20 years, specializing in MATLAB to C/C++/CUDA, Simulink to C/C++/CUDA, and machine learning deployment. As a seasoned Product Manager for MATLAB Coder, GPU Coder, and deep learning code generation, Bill is dedicated to helping engineers deploy applications in controls, signal and audio processing, embedded vision, and machine learning. He works to ensure customers can efficiently run their software across diverse platforms, from developer workstations to edge and embedded devices. Bill holds an M.S. in Electrical Engineering from the University of Southern California focusing on image and video processing and a B.A.Sc degree in Electrical Engineering from the University of British Columbia.

Jianghao Wang is a Senior Product Manager for Deep Learning and AI at MathWorks. In her role, Jianghao collaborates with users and developers to build out and deliver on MathWorks AI product strategy. Prior to that, Jianghao led the AI education initiatives at MathWorks, supporting educators and researchers on their AI projects. Before joining MathWorks, Jianghao obtained her Ph.D. in Statistical Climatology from the University of Southern California and B.S. in Applied Mathematics from Nankai University.