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: Mondays 11:35 am - 2:25 pm
- Location: Zoom
- Office hours: TBA
Announcements
- Assignmet 2 is out. Due on March 8.
- A list of topics and related papers is posted here. Please submit two papers you would like to present in-class during the term by Monday January 18, 2021.
- University of Ottawa students need to complete this form and submit it to the FGPA to gain access to CULearn.
- Lectures will be recorded (subject to any technical issue).
- See the Location above for the link to attend the class over Zoom.
- Welcome to COMP5900! We look forward to meeting you on Monday January 11 at 11:35 am over Zoom.
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 including CNNs, RNNs, GANs, Deep clustering, multiview clustering, transfer learning and domain adaptation, and Interpretability of ML methods. The format of the course will be a mix of lectures and paper presentations.
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: (25%).
- Class participation and discussion(5%).
- Final Project: (5% proposal, 5% in class presentation, 35% Report).
Course Materials
There is no required text for this course. Notes will be posted periodically in the course schedule.Paper presentations
- Submit your prefered papers for aproval before the Deadline. Late submissions will be penalized 10% per day.
- 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 these are the same as the key papers that you are going to build your course project on. Though, they can be different from your project. They can be on different topics.
- You will present one paper throughout the term. If your first prefered paper was already taken or was not qualified, I’ll go with your second preferred paper.
- Presentation should be about 20 minutes followed by about 15 minutes discussion. You should come up with a set of questions to foster a 15-minute discussion session that you will guide and facilitate after your presentation. Note that I may adjust the durations as needs arise.
- A draft of the presentation (slides) must be emailed to the instructor by the Thursday (11:59 pm) before your presentation. Late submissions will be penalized 10% per day.
- You should record your presentation in advance. Videos must be submitted via Culearn by the Friday (11:59 pm) before your presentation day. Late submissions will be penalized 10% per day.
Project
- Before you undertake your project you will need to submit (via CuLearn) a proposal for approval. The proposal should be short (max 1 page PDF). See Deadlines.
- Please consult this page for topics and a list of related papers.
- You will present your project in class near the end of term. See Deadlines
- You will submit a report on your final projetc. The report should be:
- Resources:
- Kaggle: It has a large collection of ML competitions, codes and public datasets.
- Kaggle Competitions
- Dataset Search by Google
- Physionet: It has a large collection of ML datasets/competitions mainly in health.
- Open Data @ Government of Canada
- Mimic: It is a large data set of health data associated with ~60,000 intensive care unit admissions.
- KDnuggets:
- 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. They will be a mix of coding (PyTorch) and analytical parts.
- Assignments should be submitted through CULearn. See Deadlines.
- Late submission of assignments will be penalized 10% per day and will be acepted up to five days past the deadline.