AI with Model-Based Design

In this session, we will talk about how you can incorporate AI in Model-Based Design and how MATLAB and Simulink help address the challenges of AI development for engineered systems.

Model-Based Design, the systematic use of models throughout the development process, is a proven way of developing complex systems with efficiency and reduced risks. The use of modeling and simulation has become an integral part of product development in almost all industries and is reaching new levels with the incorporation of AI models.
AI techniques complement traditional methods and have some unique advantages. However, designing systems with AI components has its own set of challenges. How can you combine the power of Model-Based Design with the benefits of AI for system development?

Learn more:
- AI with Model-Based Design Solutions: https://bit.ly/AI-with-MBD
- Integrating AI into System-Level Design: https://bit.ly/3UCOTjm
- Simulink Add-On for Reduced-Order Modeling: https://bit.ly/49zT2ZB
Virtual Sensors with AI and Model-Based Design: https://bit.ly/3UVEAr9
Guide to Understanding Reinforcement Learning: https://bit.ly/4bsprDg

About the presenters:
Tianyi Zhu is a product marketing manager for Simulink and Model-Based Design at MathWorks. He holds M.S. and B.S. degrees in Electrical and Computer Engineering, both from Carnegie Mellon University.

Arkadiy Turevskiy is a Controls and Deep Learning product manager at MathWorks. Prior to MathWorks, Arkadiy was a control and modeling engineer at Pratt & Whitney.

Chapters:
0:00 – 1:34 Presenter Intro
1:34 – 5:00 Intro and Agenda
5:00 – 10:42 3 Trends in AI + Systems
10:42 – 13:23 Model-Based Design
13:23 – 14:24 AI in Model-Based Design
14:24 – 18:02 Use Case #1: Virtual Sensors
18:02 – 20:17 Embedded AI Workflow
20:17 – 26:05 TensorFlow Model Import and Simulink Simulation
26:05 – 27:52 AI V&V: Baseline Testing
27:52 – 29:21 AI V&V: Back-to-Back Testing
29:21 – 30:39 AI V&V: Robustness Testing
30:39 – 32:00 AI V&V: Out-of-Distribution Detection
32:00 – 33:13 Model Compression: Motivation
33:13 – 34:12 Model Compression: Techniques
34:12 – 35:26 Design Space and Model Selection
35:26 – 36:16 Model Compression: Data types
36:16 – 36:58 Model Compression: Case Study
36:59 – 37:56 Code Generation and Hardware Targets
37:56 – 39:08 Processor-in-the-Loop (PIL) Simulations
39:08 – 40:29 Q&A #1
40:29 – 45:35 Use Case #2: System Identification and Reduced-Order Modeling (ROM)
45:35 – 45:57 AI-Based ROM Workflow
45:57 – 50:19 Simulink Add-On for ROM
50:19 – 53:18 Q&A #2
53:18 – 54:49 Use Case #3: Reinforcement Learning
54:49 – 55:47 Reinforcement Learning: Toolbox
55:47 – 56:06 Reinforcement Learning: Workflow
56:06 – 56:41 Reinforcement Learning: User Stories
56:41 – 57:50 Other Use Cases
57:50 – 59:35 Why MATLAB & Simulink?
59:35 – 1:00:11 Learn More
1:00:11 – 1:03:27 Q&A #3
1:03:27 – 1:04:35 Wrap-Up


--------------------------------------------------------------------------------------------------------
Get a free product trial: https://goo.gl/ZHFb5u
Learn more about MATLAB: https://goo.gl/8QV7ZZ
Learn more about Simulink: https://goo.gl/nqnbLe
See what's new in MATLAB and Simulink: https://goo.gl/pgGtod

© 2023 The MathWorks, Inc. MATLAB and Simulink are registered trademarks of The MathWorks, Inc.
See www.mathworks.com/trademarks for a list of additional trademarks. Other product or brand names may be trademarks or registered trademarks of their respective holders.