CSCI 493.77 Spring 2024

DEEP LEARNING

Participants will acquire hands-on experience in building and training neural networks, as well as a deep theoretical foundation that is firmly based on mathematical principles. No prior experience in machine learning is necessary. The initial weeks are dedicated to establishing a solid foundation in machine learning fundamentals, followed by an in-depth exploration of deep learning algorithms. A background in calculus, linear algebra, and Python programming is essential for this course.

Team-taught with Professor Susan L. Epstein

Required text Hands-on Machine Learning with Scikit-Learn, Keras & TensorFlow, A. Géron, 3rd edition. ISBN 13: 9781098125974.

Course Documents

Lab Notebooks content list

Course Syllabus (available to students via Blackboard)

Course Schedule (available to students via Blackboard)

Lab Notebooks (available to students via Blackboard)

Review Notes

• Machine Learning Notes

• Deep Neural Networks Notes

• Convolutional Neural Networks

• Recurrent Neural Networks

• Transformers

• GANs

• Diffusion models