This course will broadly deal with deep learning methods for natural language processing, with a specific focus on large language models. Most of the semester will focus on neural language models. It is intended for graduate students in computer science and linguistics who are (1) interested in learning about cutting-edge research progress in NLP and (2) familiar with machine learning fundamentals. We will cover modeling architectures, training objectives, and downstream tasks (e.g., text classification, question answering, and text generation).

In-depth introduction to Artificial Intelligence focusing on techniques that allow intelligent systems to reason effectively with uncertain information and cope limited computational resources.

An in-depth examination of principles of distributed systems and advanced operating systems. Topics include client-server programming, distributed scheduling, virtualization and cloud computing, distributed storage, IoT. Familiarity with an undergraduate course on operating systems (COMPSCI 377 or equivalent) is helpful.

Optimization techniques are frequently used in many areas of computer science, in particular in machine learning, to handle a variety of large-scale, data intensive problems. Moreover, algorithmic tools of ever-increasing sophistication are introduced at a fast pace, offering unparalleled opportunities to solve problems efficiently. This class will cover a wide range of optimization methods, including convex, nonconvex and discrete optimization.

Covers topics such as the relational model, query languages, database design; storage and indexing, query processing and optimization, transaction management; scalability and parallelization, big data systems; cloud databases; graph data; database management systems and machine learning.

This course examines sociotechnical problems with existing modes of social media and works towards building new, affirmative visions for social media through technical and policy means. Students will examine interventions to address problems with contemporary social media and design and develop possible interventions.

The design and analysis of efficient algorithms for important computational problems. Paradigms for algorithm design including Divide and Conquer, Greedy Algorithms, Dynamic Programming; and, the use of Randomness in Algorithms. Algorithms for Sorting and Searching, Graph Algorithms, Matroid, Linear Programming, Proving NP completeness, Approximation Algorithms for NP Complete Problems, and others. Prerequisites: The mathematical maturity expected of incoming Computer Science graduate students, knowledge of algorithms at the level of COMPSCI 311.

This course is intended to serve as an advanced overview of robotics spanning the complete autonomy loop: perception, planning, and control. We will study the theory, algorithms, and efficient implementations related to these topics, with focus on open discussions for how to do research to go beyond the state of the art. Students will gain hands-on experience in implementing, and extending such algorithms using simulations.

Students will work collaboratively to construct production-grade software used to advance the goal of Child Rescue. This course is a group-based, guided independent study. Our goal is to build practical machine learning models to be used by professionals dedicated to rescuing children from abuse. Students will be encouraged to design and build their own diagnostic and machine learning tools, while also learning from professionals in the fields of digital forensics and law enforcement.

Not available at this time