Coursera Flash Sale
40% Off Coursera Plus for 3 Months!
Grab it
Learn how to deploy Reduced Order Models (ROM) of complex systems on microprocessors using TinyML in this technical talk from MathWorks engineers. Explore compression techniques like architecture search, pruning, and quantization to accelerate model inference on low-cost, energy-constrained embedded devices. Follow the workflow from developing large-scale non-linear models through training ROMs with input-output data, generating C/C++ code, and deploying to embedded targets. Examine a practical case study of State of Charge estimation for battery management in virtual vehicles to understand how this approach effectively captures complex system dynamics while reducing computational demands for both simulations and real-time applications.
