Foundations of Machine Learn

3 Credits · Level: Graduate, Undergraduate

This course provides a comprehensive introduction to the core principles and methodologies of machine learning. The course is designed to cover essential topics such as probability theories, common distributions, point estimation, sampling, model selection, gradient optimization, and evaluation, ensuring a comprehensive understanding of the theoretical and algorithmic aspects of machine learning and providing fundamental concepts to support further study in supervised learning, unsupervised learning, and reinforcement learning, It will also cover cutting-edge topics such as shallow learning vs. deep learning, self-supervised learning, and high-dimensional learning, focusing on enabling students to understand the theories and principles behind the latest advancements in the field. By the end of this course, students will not only grasp the fundamental concepts of machine learning but also cultivate a mindset and skill set that are adaptable to the dynamic nature of technological progress, keeping pace with the rapidly evolving technological landscape in the field of machine learning. The class will have lectures, mathematical homework, and exams.