Fundamentals of machine learning methods. Supervised, unsupervised, and reinforcement learning concepts, and fundamentals of fuzzy logic. Review of probability and optimization. Linear regression. Linear classification and logistic regression. Components of modern machine learning approaches, including feature engineering, neural network models, training and evaluation methodology, and deep learning libraries. Object detection and object/human pose regression for robotic applications. Bias in machine learning algorithms. Corequisite: MCTR 399.