If you have any concerns or questions, feel free to reach out to the Instructor listed (for course content questions) or grad-advising@cs (for general registration troubleshooting). You can also schedule an appointment with a grad adviser if needed. If you are interested in taking a CSE 500-level course and need an add code (any non-major), then please review the enrollment petition information on the CSE Non-Major Registration page under "Ph.D./Doctoral Courses (CSE 500 level)".

Each section has a field designated Non-major Enrollment: that provides information on if the course allows for students outside the Allen School Ph.D. program, and how to apply if it does. If you are an Allen School student (Ph.D. or 5th-year), you typically will not need an add code or to apply for enrollment. You can contact grad-advising@cs for registration assistance if needed.

The section marked with an Mailing List: is the mailing list for the course. You're welcome to use it to contact the instructors for questions.

    • Description: ML workloads have become an integral part of datacenter-based computing services. In this course, we will study the various parts of the systems stack required to support such workloads, starting from the underlying architecture and the compiler and moving on to network stacks and distributed systems. We will examine how to improve the efficiency of both training and inference systems, study the capabilities of different frameworks, analyze the needs of different ML workloads, and explore ways existing systems can be enhanced.
      Prerequisites: CSE major and upper division systems course (e.g., CSE 451 or CSE 452 or CSE 461).
    • Description: In this course we will study several techniques developed in the last 30 years to sample from sophisticated probability distributions of exponential size. We mostly focus on the applications of the Markov chain Monte Carlo method in efficient sampling and counting. The first half of the course will focus on classical techniques such as (path) coupling and the canonical path method. In the second half will study more recent developments such as the spectral independence and entropic independence machinery and applications in sampling bases of matroids and independent sets of a graph.
      Prerequisites: No prerequisites are necessary but students are advised to have taken CSE 521 (or 525) prior to taking this course.
    • Description: Once considered far from practical, continuous advances in efficiency of cryptographic tools over the past two decades have opened up their use in the design of systems providing strong privacy guarantees for users. This graduate level course will provide an overview of these powerful cryptographic tools including multi-party computation, zero-knowledge proofs, and differential privacy, and discuss their use in the design of real deployed systems enabling privacy-preserving messaging, payments, machine learning, and more.
      Prerequisites: CSE major cryptography course or equivalent (e.g., CSE 426).
    • Description: Deep Learning has become ubiquitous in our society, with applications in search, image understanding, apps, mapping, medicine, drones, and self-driving cars. Core to many of these applications are visual recognition tasks such as image classification, localization and detection and language understanding tasks like summarization, text generation and reasoning. Recent developments in neural network (aka “deep learning”) approaches have greatly advanced the performance of these state-of-the-art systems.
      This course is a deep dive into the details of deep learning algorithms, architectures, tasks, metrics, with a focus on learning end-to-end models. We will begin by grounding deep learning advancements particularly for the task of image classification; later, we will generalize these ideas to many other tasks. During the 10-week course, students will learn to implement and train their own neural networks and gain a detailed understanding of cutting-edge research in deep learning. Additionally, the final assignment will give them the opportunity to train and apply multi-million parameter networks on real-world vision problems of their choice. Through multiple hands-on assignments and the final course project, students will acquire the toolset for setting up deep learning tasks and practical engineering tricks for training and fine-tuning deep neural networks.
      Prerequisites: Linear algebra (e.g. Math 208) and Calculus (e.g. Math 124, 125).
    • Description: TBA
    • Description: TBA
    • Description: Valid experimental designs, sound data analyses, and reproducibility of empirical results are core tenets of the scientific method -- crucial not only for specific domains in computer science but rather any field that seeks empirical evidence.

      This course covers qualitative and quantitative research methods and focuses on properly designing experiments and observational studies, choosing appropriate statistical methods and models, and reasoning about the validity of experimental designs (in terms of internal, external, and construct validity). This course involves lectures, paper discussions, as well as a hands-on experience for data analysis and visualization with R.
    • Description: Brains are remarkably complex, massive networks of interconnected neurons that underlie our abilities to intelligently sense, reason, learn, and interact with our world. Technologies for monitoring neural activity in the brain are revealing rich structure within the coordinated activity of these interconnected populations of neurons. In this course, we will discuss machine learning models that can be applied toward 1) understanding how neural activity in the brain gives rise to intelligent behavior and 2) designing algorithms for brain-interfacing biomedical devices. Topics will include basic neurobiology, classical probabilistic machine learning foundations, and modern deep learning approaches, including variational autoencoders and recurrent neural networks. Coursework will include readings from the machine learning and computational neuroscience literature, programming assignments, and a final modeling project applied to neural population data.
    • Description: Computing Education Research (CER) is the study of how people learn to use programmable and/or trainable technologies. It includes computer science education, as well as other contexts where people learn how to boss computers around to pursue their own interests. Accountants learning to program macros in Excel, biologists learning Python to crunch their data, and children creating interactive stories in Scratch are all people and activities that CER attends to. So are experienced software engineers learning to weave machine learning into their applications, CS graduate students getting their heads around dependent types, and teachers figuring out how to integrate computing into their courses. CER studies learning, and how to support it, using a variety of methods, including design.

      This graduate seminar will provide students with a broad understanding of the history and state of the field, including classic systems and research as well as emerging areas of inquiry. We will read and discuss papers from CER, statistics education, science education, and the learning sciences. Students will write a research proposal that charts how we could deepen our collective knowledge about how people learn computing.
    • Description: TBA
    • Description: TBD
    • Description: TBA
    • Description: TBA
MyPlan

  • Collaborative course offerings for 23-24 will be updated as information becomes available.

    • Description: A taste of current research in Computational Biology (local and non-) + critical reading of literature + presentation skills. Students, with faculty advice, pick and present CompBio papers from recent journals/conferences. Students & faculty also present their own research (mostly in Spring, but may be sprinkled throughout, depending on schedules). Background knowledge of biology is not assumed; come learn!
    • Non-major Enrollment: The seminar is interdisciplinary, and non-majors are welcome. Email instructor for permission and forward confirmation to grad-advising@cs.washington.edu in order to receive an add code.
    • Mailing List: See Webpage
    • Description: Change is a group of faculty, students, and staff at the UW who are exploring the role of information and communication technologies (ICT) in improving the lives of underserved populations, particularly in the developing world (though domestically as well). We cover topics such as global health, education, micro finance, agricultural development, and general communication, and look at how technology can be used to improve each of these areas.
    • Non-major Enrollment: The seminar is interdisciplinary, and non-majors are welcome. Email instructor for permission and forward confirmation to grad-advising@cs.washington.edu in order to receive an add code.
    • Mailing List: http://changemm.cs.washington.edu/mailman/listinfo/change
    • Description: Computer scientists ask what it means for a work or process to be "creative" seriously, seeking formal models and tools to help humans and computers define, explore, and augment solution spaces together. We will cover foundational work on computational approaches to creativity as well as modern applications of this work to fields including the visual arts, music, mathematics, and the sciences.

      The seminar will consist of weekly discussions of readings that help us understand creative processes more formally and computationally. Participants are asked to take one hour a week for reading preparation, and to co-lead one discussion. We have background readings prepared, and are looking forward to selecting additional readings based on everyone's research and hobbies. It should be a fun time!
    • Non-major Enrollment: The seminar is available for all UW students and the content is designed to be widely accessible. Email instructor for permission and forward confirmation to grad-advising@cs.washington.edu in order to receive an add code.
    • Mailing List: N/A
    • Description: Are you interested in discussing different approaches to teaching Computer Science? Are you wondering what kind of research people do in CS education? Are you thinking about a career that involves a lot of CS teaching?A seminar for people interested in discussing topics related to Computer Science education. The format for this quarter will be a weekly discussion of readings from a variety of sources such as CS education conferences (e.g. SIGCSE, ITiCSE, ICER), journal articles on teaching approaches, or excerpts from books on teaching. Participants will be expected to do the readings, participate in weekly discussions, and co-lead one of the discussions.
    • Non-major Enrollment: Complete the 590E enrollment request form.
    • Description: The seminar will consist of weekly discussions of readings that help us understand creative processes more formally and computationally. Participants are asked to take one hour a week for reading preparation, and to co-lead one discussion. We have background readings prepared, and are looking forward to selecting additional readings based on everyone's research and hobbies. It should be a fun time!
    • Non-major Enrollment: Email instructor for permission and forward confirmation to grad-advising@cs.washington.edu in order to receive an add code.
    • Description: A weekly seminar held on Fridays at noon, run by HCI PhD students, where we gather informally to discuss new and foundational HCI literature, get to know one another, and learn together. Typically, it's a mixture of guest speakers, paper discussions, and informal conversations about HCI research. HCI Seminar is intended primarily for graduate students who do HCI research with CSE faculty members.
    • Non-major Enrollment: Open to students who are research-active with relevant CSE faculty. Email grad-advising@cs.washington.edu with your request, specifying who you are research-active with, in order to receive an add code.
    • Description: DUB is a grassroots alliance of faculty, students, researchers, and industry partners interested in Human Computer Interaction & Design at the University of Washington.

      Our mission is to bring together an interdisciplinary group of people to share ideas, collaborate on research, and advance teaching related to the interaction between design, people, and technology.
    • Non-major Enrollment: Student researchers can email instructor for permission and forward confirmation to grad-advising@cs.washington.edu in order to receive an add code.
    • Mailing List: http://dub.uw.edu/mailman/listinfo/dub
    • Description:
    • Description:
    • Non-major Enrollment: Email instructor for permission and forward confirmation to grad-advising@cs.washington.edu in order to receive an add code.
    • Description:
    • Non-major Enrollment: Email instructor for permission and forward confirmation to grad-advising@cs.washington.edu in order to receive an add code.
    • Description: Weekly seminar organized by database faculty and students where we read papers on exciting topics related to data management.
    • Non-major Enrollment: The seminar is available for all UW students and the content is designed to be widely accessible. Email instructor for permission and forward confirmation to grad-advising@cs.washington.edu in order to receive an add code.
    • Mailing List: data-science-seminars@cs.washington.edu
    • Description: The Robotics Colloquium features talks by invited and local researchers on all aspects of robotics, including control, perception, machine learning, mechanical design, and interaction. The colloquium is held Fridays between 1:30-2:30pm.
    • Non-major Enrollment: Email instructor for permission and forward confirmation to grad-advising@cs.washington.edu in order to receive an add code.
    • Description: Only for Linda Shapiro's research students in CSE, ECE and BIME.
    • Non-major Enrollment: Only students who are doing research with Linda Shapiro.
    • Description: The seminar is for students and faculty members to explore research in accessible computing for people with disabilities in the context of human-computer interaction (HCI). The seminar consists of short student presentations of current research results, followed by discussion and critical evaluations the research.
    • Description: A seminar for first year PhD students focused on enriching students' sense of belonging, camaraderie and purpose in their first year in the program. The seminar also addresses advising, choosing research problems, and the core skills needed to thrive in the Ph.D. program and beyond, including making engaging presentations and writing clearly, time management and work-life balance. Meets 3-4 times per quarter.
    • Description: The focus of this quarter is on papers (to be selected by participants) appearing in recent computer security & privacy or security & privacy-adjacent venues. All enrolled participants are expected to present at least one paper and to attend the rest of the presentations.
    • Non-major Enrollment: Email instructor for permission and forward confirmation to grad-advising@cs.washington.edu in order to receive an add code.
    • Mailing List: https://mailman.cs.washington.edu/mailman/listinfo/uw-security-research
    • Description:
    • MyPlan

    • Description:TBA
    • Description:TBA
    • CSE 590 (D): Database
    • Instructor: Dan Suciu ()
    • Course Website: TBA
    • Description:
    • CSE 590 (O): TBA
    • Instructor: Luis Ceze ()
    • Course Website: TBA
    • Description:
    • Description:
    • Description:
    • MyPlan