In this course, you will learn the fundamentals of deep learning, understand how to design neural networks, and apply them to specific c problems. Topics include an overview of artificial neural networks, convolutional neural networks, recurrent neural networks, deep generative models, deep reinforcement learning, and recent research topics and applications on audio-visual and language understanding.
DS 506 Machine Learning for Natural Language Processing
Nature Language Processing is an interdisciplinary field of linguistics, computer science, and artificial intelligence where the goal is to develop algorithms to understand human language. In this course, students will first learn about how to turn text data into features that can be used as input to machine learning methods. They will also learn about n-gram language models, part-of-speech tagging, vector space models, and locality-sensitive hashing. The last part of the course will include the recent deep learning models (attention models, siamese networks, transformers) that improve the performance in several NLP tasks.
DS 590 Graduation Project
Students complete a theoretical or practical approach for solving a selected problem in deep learning.