This is a previous offering of this course. For Fall 2022 offering, visit here.
General Information
- Instructor: Majid Komeili
- Email: majid.komeili@carleton.ca
- Time: Tuesdays 11:35 am - 2:25 pm
- Location: Paterson Hall 133
- Office hours: by email appointment, in HP 5436
Announcements
- The final project report is due on Dec. 14. Submit your report (pdf only) along with your codes (zip file) through CuLearn.
- Project presentations on Tue Dec 3: Please use this form to upload your slide(s) by 11 am before class.
- See the correction to Assignment 2, Question 5 here.
- Assignment 2 is out. (
Due on Oct. 29Extended deadline Nov 1) - Invitations to join the course workspace on Slack is sent to your emails. We will use Slack to facilitate the after class discussions.
- Please use this form to submit the final version of your slides after your presentation.
- Assignment 1 is out. (Due on Oct. 8)
- A tentative schedule for reviewing papers is posted in the course schedule.
- See the course schedule for slides.
- A list of topics and related papers is posted here. Please submit the two papers you would like to present in-class during the term by Tuesday September 17, 2019.
- University of Ottawa students need to complete this form and submit it to the FGPA to gain access to CULearn.
- Carleton University students from outside School of Computer Science will need my permission to be able to register in this course. Please fill in this form.
- Welcome to COMP5900! We look forward to meeting you on Tuesday September 10 at 11:35 am at Paterson Hall 133!
Description
Machine learning (ML) is the scientific study of algorithms and statistical models that computers use in order to perform a specific task effectively without using explicit instructions, relying on patterns and inference instead. It is seen as a subset of artificial intelligence. This course will cover advanced topics in machine learning such as deep learning, transfer learning, multiview learning, clustering and Interpretability of ML methods.
Course Information
Prerequisites
You are expected to have a reasonable background in machine learning and be familiar with probability, statistics, linear algebra and calculus.Evaluation
- Two assignments (A1=10%, A2=15%)
- Paper presentations (30%)
- Class participation and discussion(5%)
- Final Project (35% Report, 5% in class presentation)
Course Materials
There is no required text for this course. Notes will be posted periodically in the course schedule.Paper presentations
- This includes choosing two papers from ML journals and conferences and presenting them in class. Please consult this page for topics and a list of related papers.
- Ideally they are the same as the key papers that you are going to build your course project on them. Though, one or both can be different from your project.
- Submit your prefered papers before the Deadline.
- Presentation should be about 20 minutes followed by about 15 minutes discussion. A draft of the presentation (slides) must be sent to the instructor by Friday before your presentation.
Project
- Please consult this page for topics and a list of related papers.
- Submit a brief proposal using this form. See Deadlines.
- Project presentation will be in class on Dec. 3.
- Final Report:
- Resources:
- Kaggle: It has a large collection of ML competitions, codes and public datasets.
- Physionet: It has a large collection of ML datasets/competitions mainly in health.
- Mimic: It is a large data set of health data associated with ~60,000 intensive care unit admissions.
- UCI Machine learning repository: It has a large collection of standard ML datasets.
- Papers in conferences such as NeurIPS, ICML, AAAI, EMNLP , ACL, CVPR
- Papers in journals such as TPAMI, TCYB, TNNLS, JMLR
Assignments
- There are two assignments which will be posted on the course website.
- Assignments should be submitted through CULearn. See Deadlines.
- Late submission of assignments will be penelized 10% per day.