General Information

    When and Where: Mon/Wed, 1:00-2:50PM, Phelps 2510

    Professor: Ben Zhao, ravenben at cs.ucsb.edu

    Office Hours:

    • Ben: Wed 10-11am @ my lab: Phelps 3534

    NOTE: Final presentations, Wed Dec 9, 4-7PM, Phelps 2510

    Class Email List: CS290 class page on Piazza

    Prerequisites: Solid background in networking, systems (CS176B or equivalent, CS170 or equivalent).

Introduction

Machine learning is rapidly becoming mainstream as a set of critical tools that extend the capabilities of data-driven systems in a variety of research areas. This class will not focus on developing new theories or methods in machine learning. Instead, we will focus on understanding the best, most creative and inventive ways to apply existing tools and techniques. We will focus on understanding tools and their limitations, and potential pitfalls.

We will focus on studying the state of the art in applied machine learning in systems, networking, security and related topics. We will focus on reading a variety of technical papers, and a single research project to be done in teams of 2-3 students. The goal of the project is to extend current ML techniques to new problems, with the end goal of producing real, publishable results by the end of the quarter. In addition, students are expected to gain experience in two valuable skills: quickly reading technical papers (without sacrificing understanding), and giving public presentations.

Textbooks

The majority of reading material for this course will come in the form of research papers. There is no required textbook.

Paper Presentations

As a CS290 special topics course, this class will focus primarily on active discussions of relevant technical papers. We will avoid any lectures by professors, and instead each student will present at least 1 paper in a detailed technical presentation (20-30 mins).

Grading Policy

Your quarter grade will be derived from your in-class presentation, active participation in discussions, and your class project:
  • Paper presentation, 35%
  • Course project, 55%
  • Class participation, 10%