34702 Topics in Networks: Machine Learning for Networking and Systems, Autumn 2021

Latest Announcements

Welcome to Autumn 2021

Overview

34702 is a graduate seminar course in systems.

The modern ML revolutions (deep learning, big data, etc) have transformed the landscape of many computing domains, including computer networks and systems. This course will cover recent research that applies machine-learning and data-driven techniques in networking and systems ("ML for networks/systems"). Through case studies, we will discuss why/how ML is uniquely suitable for many (though not all) systems problems and, more importantly, how to do interdisciplinary research between systems and other computing domains.

This course assumes a basic familiarity with networking and operating sytems concepts. The course will consist of a reading/lecture/discussion component and a project component. Each class will cover approximately 2-3 research papers. Some of these papers will introduce students to the basic principles on which modern networked systems and distributed systems are based. Others will cover more recent work to explore the state of the art and observe the evolution of these systems over time.

Students are expected to read papers before the class and participate in the discussion during the class.


Course Staff

Instructor

NameEmailOfficeTelOffice Hours
Junchen Jiang JCL 367 - By Appointment

Grading

Your final grade for the course will be based on the following weights:

The project in 34702 is an open-ended research project, done in groups of two or three. The project requires a proposal and a short presentation. You are welcome to attend the seminar even if you are not taking the class for a letter grade. If you take the class for a letter grade, it counts as a systems elective for PhD students and as a CMSC elective (as well as towards honors credit) for undergraduates.

Course Policies

Project

The project presentations must be given on the day they are scheduled.


Last updated: 09/21/2021