MSDA3440

Description

This course addresses current or timely topics in Data Analytics. Special Topics can vary from semester to semester. Course may be repeated for credit if topics are different. Fall 2023 3440-01 - Deep Learning This course covers modern artificial intelligence algorithms based on deep neural networks. It starts with a review of the necessary statistics and mathematical background and then provides in-depth coverage of the different types of neural network architectures and their training algorithms. The next step is going with a detailed explanation of different types of deep learning architectures such as deep convolution networks, sparse autoencoders, recurrent neural networks, belief networks, transformers, and reinforcement learning techniques. Moreover, the course introduces a wide variety of projects using the explained deep networks through state-of-the-art Python libraries. Applications of deep learning to computer vision, text classification, speech recognition, and optimization problems are presented. The course also introduces the basic concepts of natural language processing (NLP) and how it can be considered using deep neural architectures. Several recent research papers will be explained in the lectures and a comprehensive research project will be assigned as part of the course. Spring 2024 3440-01 Applied Natural Language Processing Prerequisites: MSDA 3050 and MSDA 3040 Natural Language Processing (NLP) is a rapidly advancing domain, encompassing areas such as the hard sciences, humanities, and social sciences. Its applications are highly regarded across academia, government, and industries. This course delves into the intricacies of NLP algorithms, emphasizing their real-world application. A significant portion of the topics will be dedicated to understanding both generative and non-generative models in NLP, exploring their strengths, weaknesses, and use-cases. Students will gain insights into how these models' function, their underlying mechanisms, and their practical implications in natural language tasks. The course sheds light on the core issues and resolutions in NLP, illustrating their connections with linguistics and statistics. It provides a comprehensive insight into the methodologies used by computers to interpret and produce human language, integrating key principles from Applied Machine Learning and Data Engineering. Designed as an interactive lecture series, active student involvement is paramount. Weekly prescribed readings will complement lectures, and students are advised to review them before classroom discussions. All course content, from readings and lecture presentations to assignments, will be accessible via the online Learning Management System (LMS). Three lecture hours per week, plus programming work outside of class.