This course will cover how computing technology is moving beyond desktop computers and becoming increasingly integrated into everyday environments. It will be offered in a seminar-style format involving readings of academic papers, student-led presentations, and a course project.

The software and internet industries; principles of operation for successful software enterprises; innovation and entrepreneurship; software business definition and planning; business models, market and product planning; product development, marketing, sales, and support; financial management and financing of high-technology ventures; management, leadership, and partnerships. Students will all write business plans in teams.

This is an advanced seminar with a significant term (research) paper required of all students and several presentations during the term. Each term, four current research topics in computational linguistics will be chosen for deep investigation, exploring the research and secondary literature.

Introductory course covering the foundations of computational imaging. Topics include basic image processing, convolutional neural networks for image processing, digital photography, inverse problems in imaging, proximal gradient methods, introduction to wave optics, time-of-flight imaging, and end-to-end optimization of optics and imaging systems. Emphasis on applications and solving inverse problems using classic algorithms, formal optimization, and modern machine learning techniques.

This course covers several topics in machine learning theory. The first half focuses on uniform convergence-based methods (e.g., covering, chaining) to establish generalization through complexity measures like Rademacher complexity and VC dimension. Second half starts with reproducing kernel Hilbert spaces and demonstrates double descent phenomenon in a kernel ridge regression setup. Finally, we discuss linearization (NTK) and feature learning in neural networks.

This will be a seminar-style course, covering a combination of seminal work and recent advances in computer science education and related fields, drawing on methods and theories from Computer Science Education, Learning Sciences, Human-Computer Interaction, and Educational Technology. Students will conduct weekly readings, with student led presentations and discussions each week. A final project will make up a large part of the grade, while student presentation skills and participation in class and in readings will also be emphasized. Students will learn how to design and evaluate interactive learning systems and educational technologies, and how to critically examine and evaluate both qualitative and quantitative research studies in CS Education.

This course will study techniques and algorithms for creating effective visualizations based on principles from graphic design, visual art, perceptual psychology, and cognitive science. The course is targeted both towards students interested in using visualization in their own work, as well as students interested in learning about cutting edge research in the field. Students will conduct reading and critical analysis of scientific research papers, that will be discussed in class. A final project will make up most of the grade, while student presentation and critical analysis skills will also be emphasized.

An advanced seminar course on selected topics in computer vision and computational imaging. Topics will be based on a collection of papers from the current literature as class reading.

Computational cognitive modeling is an increasingly key aspect of artificial intelligence (AI). As AI is deployed in systems that touch every aspect of people's life and work, modeling of intelligent behaviour needs to be cognizant of human ways of thinking and knowing. This is especially true in the area of language, where successful communication depends on an AI having linguistic representations compatible with human expectations. Research in computational linguistics and in cognitive modeling of language has consequently seen a growth in fruitful exchange of ideas and technologies. In this course, students will learn about key computational models for semantics and pragmatics of language that draw on cognitive theories, as well as cognitive approaches that benefit from recent advances in machine learning. This seminar will have weekly reading assignments and in-class discussion sessions interspersed with hands-on computational modeling. Students will develop their own project proposal or select one recommended by the instructor. The course grade will be based on weekly reading responses, participation in class discussion, a class presentation, a project proposal, and a final project.

This course will involve discussion of recent developments in machine learning based on discussions of research papers. Topics may involve deep learning and its applications, foundation models, ethical, societal, and safety implications of ML, and questions of efficiency and scalability.

This is a seminar course that explores recent advances in knowledge representation an reasoning. The course draws predominantly on research readings. The format of the course is a mix of class lectures, seminars, and student paper presentations. Students are typically required to complete a course project.

This course will involve a discussion of several recent developments in machine learning research based on a collection of ML research papers. Topics may include basic learning algorithms, representation learning, ML theory, and application specific aspects of ML research. The course can involve case studies of contemporary ML problems and pipelines.

This course offers an introduction to current topics and methods in computational neuroscience. Theoretical analysis and computational methods are tools for characterizing what nervous systems do and determining how and why they do it. Neuroscience encompasses approaches ranging from molecular studies to human psychophysics. Computational neuroscience encourages cross-talk between the many levels of this broad field by constructing compact descriptions of what has been learned at various levels, building bridges between these descriptions, and identifying potential unifying concepts and principles. This course will cover the basic methods used for these purposes and discuss examples in which computational approaches have yielded insight into brain function.

In recent years, Deep Learning has become a dominant Machin Learning tool for a wide variety of domains. One of its biggest successes has been in Computer Vision where the performance in problems such as object and action recognition has been improved dramatically. In this course, we will be reading up on various Computer Vision problems, The state-of-the-art techniques involving different neural architectures and brainstorming about promising new directions.

This course is designed to introduce students to the field of physics-based animation by exposing them to the underlying mathematical and algorithmic techniques required to understand and develop efficient numerical simulations of physical phenomena such as rigid bodies, deformable bodies and fluids. In physics-based animation we will learn how to develop algorithms that produce visually compelling representations of physical systems. We will learn the underlying continuous mathematics describing the motion of physical objects, explore how to discretize them and how to solve the resulting discrete equations quickly and robustly. Topics covered include rigid body simulation, elasticity simulation, cloth simulation, collision detection and resolution and fluid simulation. Along the way, we will explore the underlying mathematics of ordinary differential equations, discrete time integration, finite element methods and more.

Computational and algorithmic systems are now embedded in all parts of society, which introduces both great opportunities and challenges. This course presents an introduction to computational social science, a rapidly growing interdisciplinary field that studies questions at the intersection of AI, data, and society. We focus on the spectrum of methodologies now available for conducting social research in the digital age, from large-scale observational studies to online experimentation, as well as research skills including reading state-of-the-art papers, writing reviews, and doing a research project. Topics covered will include online misinformation, algorithmic bias, and social media platforms.

This course surveys algorithms that aid a group of biological or artificial agents in making collective decisions. The course specifically focuses on the area of computational social choice, which lies at the intersection of computer science and economics. This area has recently seen a growing number of real-world applications and this course reviews the theoretical foundations at the core of its success. The course will investigate issues which arise when a group of agents interact. This includes fairness, efficiency, preference elicitation, and strategic manipulations. These will be examined through frameworks of social choice theory (voting, fair division, matching, and facility location), mechanism design (auctions), and non-cooperative game theory (Nash equilibria, price of anarchy, and congestion games).

This course will explore how to use randomized A/B/N experiments to compare alternative intervention components and to continuously enhance the design of digitally delivered interventions, so that these interventions are intelligently adaptive in trying to better help people change behaviour and achieve their goals. The course draws on Human-Computer Interaction topics around design and prototyping of interventions, Social-Behavioural Science theory and methods for understanding and impacting human behaviour, Artificial Intelligence applications like LLMs (Large Language Models) for designing and adapting interventions, Machine Learning algorithms for adaptively analyzing and adjusting experiments, and Statistical methods for analyzing traditional and adaptive A/B/N experiments.

This course will cover qualitative and quantitative methods from human-computer interaction and how they are applied in research areas like healthcare and education. Examples of methods include participatory design, interviews, and field deployments. It will be offered in a seminar-style format involving readings of academic papers, student-led presentations, and a course project.

The deployment of machine learning in real world systems calls for a set of complementary technologies that will ensure that machine learning is trustworthy. Here, the notion of trust is used in its broad meaning: the course covers different topics in emerging research areas related to the broader study of security and privacy in machine learning. Students will learn about attacks against computer systems leveraging machine learning, as well as defense techniques to mitigate such attacks. The course assumes students already have a basic understanding of machine learning. Students will familiarize themselves with the emerging body of literature from different research communities investigating these questions. The class is designed to help students explore new research directions and applications.

This is a topics course in computer science. The topic will change from year to year and may span a variety of different topic in computer science.

This course will cover innovative human-computer interaction technologies that are being used across disciplines to solve real-world problems. These technologies include but are not limited to virtual reality (VR), augmented reality (AR), haptics, and generative AI. It will be offered in a seminar-style format involving readings of academic papers, student-led presentations, and a course project.

Students will learn fundamental methodologies, tools, and concepts for continuum robotics. The course covers continuum robot structures, constant curvatures kinematics frameworks, inverse and differential kinematics, trajectory planning and collision free motion planning, as well as sensing and control.

Words are fundamental components of human language, but their meanings tend to change over time; e.g., face ('body part' -> 'facial expression'), gay ('happy' -> 'homosexual'), mouse ('rodent' -> 'device'). Changes like these present challenges for computers to learn accurate representations of word meanings — a task that is crucial to natural language systems. This course explores data-driven computational approaches to word meaning representation and semantic change. Topics include latent models of word meaning (e.g., LSA, word2vec), corpus-based detection of semantic change, probabilistic diachronic models of word meaning, and cognitive mechanisms of word sense extension (e.g., chaining, metaphor). The course involves a strong hands-on component that focuses on large-scale text analyses and seminar-style presentations.

Computing and Global Development is designed to develop a critical understanding of international development and its relationship with computing technologies. This course will draw from various established and growing fields of academic scholarship including Information and Communication Technology and Development (ICTD), Human-Computer Interaction (HCI), Development Sociology, Science and Technology Studies (STS), and Political Economy.

This course introduces critical social analysis of the ethical aspects of Artificial Intelligence. Students will learn about the theories of ethics, the history of AI, the intersection between ethics and computing, the underlying values of AI, privacy concerns around AI applications, different kinds of biases (based on race, gender, age, sexual orientation, faith, geographic location, etc.) associated with many AI applications, the concerns around AI, and associated debates based on contemporary examples. This course will prepare students for systematically analyzing and auditing an AI system for its ethical standards, and designing new systems that are fairer.

This is a topics course in robotics. Topics will vary year to year.

This course will examine some of the most important papers in imitation learning for robot control, placing more emphasis on developments in the last 10 years. Its purpose is to familiarize students with the frontiers of this research area, to help them identify open problems, and to enable them to make a novel contribution.