Machine Learning for Engineers

Course overview

Engineers work with measurement data, process parameters, and test results. Machine Learning expands this work: regressions predict material properties, classifiers identify defective parts, and outlier analyses indicate disturbances. Learning Objectives Prepare measurement and process data using SQL and pandas Utilize regression with polynomial features for technical contexts Handle outliers with Median Absolute Deviation and RANSAC Train classifiers for quality inspections Employ Monte Carlo simulation and probability distributions Evaluate models using MSE, R2 value, and cross-validation Content The course begins with SQL, basic Python, pandas, and matplotlib. This is followed by linear algebra, statistics, and the central limit theorem. In the Machine Learning section, you will work with regression, regularization, decision trees, PCA, and neural networks. In the project part, you will estimate the effort of a data project, plan it in a team, and present the results. Exercises with technical datasets demonstrate how models provide predictions for components and processes. Perspectives As a development engineer, head of mechatronics development, process data analyst, or maintenance manager, you will apply Machine Learning to technical issues.

Upcoming dates

• 2026-10-11T22:00:00.000Z · 2027-06-12T22:00:00.000Z · Berlin · Hybrid Learning
• 2026-10-11T22:00:00.000Z · 2027-06-12T22:00:00.000Z · München · Hybrid Learning
• 2026-10-11T22:00:00.000Z · 2027-06-12T22:00:00.000Z · Berlin · Hybrid Learning
• 2026-10-11T22:00:00.000Z · 2027-06-12T22:00:00.000Z · Frankfurt am Main · Hybrid Learning
• 2026-10-11T22:00:00.000Z · 2027-06-12T22:00:00.000Z · Stuttgart · Hybrid Learning