This advanced course focuses on the dynamics and control of robotic systems, concepts crucial for understanding how robots move and interact with their physical surroundings. The content covered will go into greater depth than the more general course, CompSci 603 Robotics. Students will learn the kinematics and dynamics of robots with multiple degrees of freedom, as well as the analysis and control of these systems. Subjects covered include Lie group-based kinematics, Lagrangian dynamics, whole-body control, contact simulation, and actuation mechanisms.

Machine learning is the computational study of artificial systems that can adapt to novel situations, discover patterns from data, and improve performance with practice. This course will cover the mathematical foundations of supervised and unsupervised learning. The course will provide a state-of-the-art overview of the field, with an emphasis on implementing and deriving learning algorithms for a variety of models from first principles.

Machine learning is the computational study of artificial systems that can adapt to novel situations, discover patterns from data, and improve performance with practice. This course will cover the mathematical foundations of supervised and unsupervised learning. The course will provide a state-of-the-art overview of the field, with an emphasis on implementing and deriving learning algorithms for a variety of models from first principles.

This course will cover Bayesian and Markov networks; exact and approximate inference methods; estimation of the parameters and structure of graphical models; broader topics in probabilistic inference for statistics and machine learning.

This course will provide an introduction to, and comprehensive overview of, reinforcement learning (RL).

This course covers a broad range of advanced level topics in natural language processing. It is intended for graduate students in computer science who have familiarity with machine learning fundamentals. It may also be appropriate for computationally sophisticated students in linguistics and related areas. Topics include probabilistic models of language, computationally tractable linguistic representations for syntax and semantics, and selected topics in discourse and text mining. After completing the course, students should be able to read and evaluate current NLP research.

This course will focus on modern, practical methods for deep learning with neural networks. The course will begin with a description of simple classifiers such as perceptrons and logistic regression classifiers, and move on to standard neural networks, convolutional neural networks, some elements of recurrent neural networks, and transformers. The emphasis will be on understanding the basics and on practical application more than on theory. Many applications will be in computer vision, but we will make an effort to cover some natural language processing (NLP) applications as well.

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.

People are able to infer the characteristics of a scene or object from an image of it. In this course, we will study what is involved in building artificial systems which try to infer such characteristics from an image. Topics include: Basics of image formation - the effect of geometry, viewpoint, lighting and albedo on image formation. Basic image operations such as filtering, convolution and correlation. Frequency representations of images. The importance of scale in images. Measurements of image properties such as color, texture, appearance and shape.

This is an introduction to cryptography, emphasizing formal definitions and proofs of security. Though the course is theoretical in nature, its viewpoint will be "theory for practice." In particular, we will discuss cryptographic algorithms that are used in practice and how to reason about their security. More fundamentally, we will try to understand what security "is" in a rigorous way that allows us to follow sound cryptographic principles and uncover design weaknesses.