CSE 517a Home (SP19)

This is an inactive course webpage.

All course information and contents for SP2020 will be available on Canvas.

Announcements

  • Thanks for a great semester!
  • We care! Thanks for taking the time to fill out the course evals! We got a response rate of 84.5%, which is great!
  • Regradeswe cannot take any regrades after the deadlines listed below, since grades are due on THU May 9th (this is a school deadline we cannot influence).
    • implementation project and written hw
      • deadline: WED May 8th 11:59pm (midnight)
      • office hours: TUE May 7: 2-4pm (Trevor) in Jolley 431
      •  via Piazza (use grades tag)
    • application project
      • deadline: WED May 8th 11:59pm (midnight)
      • Brad can be reached via the cse517a Piazza – use tag application_project
      • office hours: WED May 8th 6-7pm (Brad) Jolley 5th floor table in the back
    • final exam
      • deadline: THU May 9th 2pm
      • office hours: THU May 9: 1-2pm (MN) in Jolley 222

Instructor: Marion Neumann
Office: Jolley Hall Room 222
Office Hours: TUE 11:30am-12:30pm
Contact: please use Piazza!

Assistants and TAs:
Trevor – Head TA (*) and (***)
Brad Flynn – Application Project Coordinator (**)
Zachary (***), JerryAdrien

* manages all grades on Gradescope/Canvas –> use Piazza tag grades
** contact for the application project –> use Piazza tag application_project
*** manages the autograder –> use Piazza tag autograder

TA Office hours:

Wednesday 10am-12pm (Trevor) in McDonnell 362
Thursday 5:30-7:30pm (Zach) in Jolly 517
Friday 10am-12pm (Jerry) in Jolly 517
Monday 2:30pm-4:30pm (Adrien) in Jolly 517

 

This course assumes a profound understanding of the fundamentals of machine learning (including the theoretical foundations and principles of ML as well as hands-on implementation experience). CSE517a covers advanced topics at the frontier of the field in-depth. Topics to be covered include kernel methods (support vector machines, Gaussian processes), neural networks (deep learning), and unsupervised learning. Depending on developments in the field, the course will also cover some advanced topics, which may include learning from structured data, active learning, and practical machine learning (feature selection, dimensionality reduction). For more information check-out the Roadmap.

Prerequisites: CSE 247, CSE 417T (enforced), ESE 326, Math 233, Math 309, and profound experience in Matlab/Octave or Python.

This class counts towards the Certificate in Data Mining and Machine Learning as required course.

Syllabus

Course Calendar and Reading

Homework Assignments

Application Project

Grades on Canvas

Resources and HowTos

Piazza (through Canvas)