MEM 5003 AI and ML Methods in Engineering Mathematics 3.0 Credits
This course introduces data‑driven modeling and learning methods that complement, but do not require, the analytical and numerical topics of Applied Engineering Mathematics I and II. Core topics include probabilistic modeling, supervised and unsupervised learning, dimensionality reduction, neural networks, Gaussian‑process surrogates, reinforcement learning for control, and physics‑informed approaches for ODE/PDE‑based systems. Foundational mathematical tools, linear algebra, optimization, and basic ODE/PDE concepts, are reviewed as needed, ensuring accessibility for students with varied backgrounds. Emphasis is placed on model validation, uncertainty quantification, and engineering applications across structures, fluids, materials, and dynamical systems.
Repeat Status: Not repeatable for credit