Applied Machine Learning for Engineers

Seminar Overview

Machine learning has moved from research lab to the engineering mainstream — surrogate models, defect prediction, process optimization, and AI-driven design are now production tools. This seminar teaches the machine-learning methods engineers actually use, grounded in the graduate-level curriculum of MIT OpenCourseWare's computer-science and AI courses. It covers supervised, unsupervised, and reinforcement learning, model selection and evaluation, and the pitfalls of applying ML to engineering data — without the mathematics mystique. The payoff: your engineers stop reading AI hype and start judging (and building) the models already arriving in your toolchain.

Ideal Learner

• Design and process engineers asked to evaluate or use ML-based tools
• CAE and simulation engineers building surrogate models
• Reliability engineers applying ML to field-failure data
• Engineering managers making AI adoption decisions
• R&D scientists bringing ML to materials and process problems

Learning Objectives

• Map ML methods (regression, classification, clustering, RL) to engineering problems
• Evaluate a model's validity, overfitting, and generalization risk on engineering data
• Build surrogate models of simulation or process behavior
• Apply ML to defect prediction, material screening, and process optimization
• Judge vendor AI claims against sound ML practice

Consulting Sessions

Seminar attendees can sign up for individual consulting sessions with the instructor. Sessions are free for registered attendees, first-come first-served — sign up when registering by calling 248-539-0473 or during the seminar.