11-962 Introduction to Machine Learning
12 units, Carnegie Mellon University
The course introduces students to the theoretical foundation of elementary Machine Learning (ML) concepts and algorithms, with a focus on how they relate to the field of Natural Language Processing (NLP). Students who complete this course will be prepared for continued graduate education in the areas of Data Science and Artificial Intelligence, and in particular we prepare students for advanced courses in Large Language Models and related topics. Students become skilled in evaluating the machine learning models (e.g. Decision Trees, Perceptron, Neural Networks, Deep Learning) that are well suited to supervised learning tasks, unsupervised learning tasks, and reinforcement learning tasks via a first principles approach (e.g. Information Entropy to motivate Decision Tree selection). Students develop practical skills with hands on coding assignments (e.g. modeling, training, testing, hyperparameter cross validation, visualization, error analysis) embedded in every aspect of the course to balance theoretical understanding with practical skills (e.g. support Gradient Descent theory with mini-batch Stochastic Gradient Descent and scheduled learning). Students will develop science communication skills required to effectively communicate their findings via data visualization and comprehensive reporting.
Prerequisites: none listed
Offered: Spring 2027, Fall 2026, Summer 2026
Courseweave needs JavaScript to show sections, workloads and planning tools.