Introduction to Machine Learning / Summer 2025
Updates
- New Lecture is up: Final Review [slides]
- New Lecture is up: Transformers [slides]
- New Lecture is up: Autoencoders (AEs) [slides]
- New Lecture is up: Generative Adversarial Networks (GANs) [slides]
- New Assignment released: [HW 4]
- New Lecture is up: Unsupervised Learning [slides]
- New Lecture is up: DL Recipe [slides]
Course Description
Machine learning is about making predictions and decisions from data. This course introduces both the theoretical foundations and practical algorithms of machine learning, viewed from multiple perspectives. Topics include linear regression, logistic regression, support vector machines, neural networks, deep learning basics, generative models, and unsupervised learning.
Prerequisites
-
Calculus and Linear Algebra (e.g., MATH 241, MATH 230 or equivalent)
You should be comfortable with taking derivatives and matrix/vector operations. -
Probability and Statistics (e.g., MATH 205, MATH 350 or equivalent)
You should be familiar with basic concepts such as random variables, Gaussian distributions, expectation, variance, and covariance. -
Python Programming
You should be comfortable with basic programming concepts, data structures, and libraries like NumPy, Matplotlib, and Scikit-learn.
Course Staff
