Machine Learning for Mechanical Engineering

Statistics in Python, data management, visualization, regression and classification models, feature engineering, usage of databases, supervised and unsupervised learning, reinforcement learning, active learning, Bayesian optimization, Gaussian process, decision trees and forests, neural networks, convolutional neural networks for mechanical engineering applications (e.g. microscopy image analysis, material structure-property relationship), atomistic descriptors, machine learning potentials for molecular dynamics, self-driving lab.