CS3350

This course is designed to provide a groundwork for both machine learning and deep learning early on in undergraduate studies. Each lecture covers fundamental topics in Machine Learning interleaved with their practical application in code, using machine learning libraries such as PyTorch to implement and experiment with the discussed concepts. Topics include training paradigms, loss functions, optimization, evaluation, hyperparameter tuning, generalization, simple neural networks, CNNs and Transformers, backpropagation, featurization, and more. This course also applies concepts from probability and linear algebra to these topics. By the end of the course, students will be prepared to take more advanced courses to deepen their theoretical and applied knowledge of machine learning and deep learning.

Prerequisites: "C-" of better in (MATH 2270 OR MATH 2271) OR ("B" or better in MATH 2250)) AND Foundational Courses complete AND (Major OR Minor in Kahlert School of Computing OR ECE).

Fall