|
CS550 - Machine Learning - Fall 2025
ANNOUNCEMENTS
This is the website for CS550, Fall Semester 2025.
Course materials, slides, assignments, etc. will be posted on Moodle.
Make sure you visit this page often enough as any announcements will be made here.
CLASS HOURS
Wed.: 11:30-12:20, Fri.: 15:30-17:20 in EA-Z03.
LECTURER
Shervin R. Arashloo
Office: EA-429
Office Hour: By appointment
E-mail: s.rahimzadeh -at- cs.bilkent.edu.tr
Teaching Assistants
Ahmet Burak Yıldırım (a.yildirim -at- bilkent.edu.tr)
Mohammad Hoseinpour (mohammad.hosein -at- bilkent.edu.tr)
COURSE DESCRIPTION
Introduction to basic machine learning concepts and algorithms. Bayesian decision theory. Dimensionality Reduction. Decision trees. Artificial neural networks. Evaluation of classification algorithms. Unsupervised learning and clustering. Genetic algorithms. Ensemble learning and classifier fusion. Kernel methods. Deep learning. Recent topics in machine learning. Reinforcement learning. Credits: 3 units
COURSE EMPHASIS AND GOALS
This course has two parts. The first part includes an introduction to the basic machine learning concepts and algorithms, which will also provide the basis for the second part of the course. The second part covers selected recent topics in machine learning. In particular, the course will cover the following main topics:
Introduction
Bayesian decision theory
Dimensionality Reduction
Decision trees
Artificial neural networks
Evaluation of classification algorithms
Unsupervised learning and clustering
Genetic algorithms
Ensemble learning
Deep learning
Kernel Methods
Reinforcement learning
TEXTBOOKS
Introduction to Machine Learning, E. Alpaydin, Second Edition, MIT Press, 2010.
Foundations of Machine Learning, M. Mohri, A. Rostamizadeh, and A. Talwalkar, Second Edition, MIT Press, 2018.
Pattern Recognition and Machine Learning, C. Bishop, Springer, 2006.
Machine Learning, T.M. Mitchell, McGraw-Hill, 1997.
Pattern Classification, R.O. Duda, P.E. Hart, D.G, Stork, Second Edition, Wiley-Interscience, 2000.
EXAMS
HOMEWORK
We will have multiple homework assignments that have some programming and some non-programming components where you are expected to work individually . These will be posted on Moodle.
Survey
You will work in a group of two. (If there is an odd number of students, one group will consis of three students.) Each group will prepare a survey on the topic of their interest by reading at least 15-20 scientific papers and writing a short report (maximum of 5 pages including references). The reports are expected to be at most 5 pages and must follow the IEEE two-column format as described in their templates. Your survey topic must be aligned with your project topic that you will choose.
In your report:
provide the problem/topic definition,
discuss the motivation behind the studies working on this problem/topic (just try to answer the question of “why have all these studies worked on this problem? is it really important?”)
and then explain the studies. While explaining these studies, do NOT simply list the studies and do NOT explain them one by one. Instead, understand the contribution and methodology of each study, try to group the studies according to their contributions and methodologies
and then explain/discuss the advantages and disadvantages of different studies as groups (like writing a good introduction section to a scientific paper).
In your discussion, do not forget to give the common approach followed by each group while also discussing the variations that exist within each group. Explain the advantages and disadvantages of each group's approach, and discuss the similarities and differences in between the approaches followed by different groups. The quality of the survey as well as those of the selected papers will affect your grade (select good papers published in prestigious conferences and journals-also include recent studies). Additionally, the format, structure, and writing style of your report (including writing the citations properly) will be a part of your grade.
Although there is no restriction for the topic that you will select (as long as it is related to the course contents), the students should seek consent from the lecturer for their topic. Since we want to minimise possible overlaps over topics, two groups will not be allowed to work on a very similar topic; The project topics will be confirmed on a first-come-first-served basis.
Examples of the topics include but are not limited to
Machine learning for computer security (or for something else)
Ensemble methods in text retrieval (or in something else)
Machine learning in finance (or in something else)
Machine learning for telecommunication networks (or for something else)
Reinforcement learning for computer games (or for something else)
Deep learning for medical image segmentation (or for something else)
Deep learning in robotics (or in something else)
Active learning for remote sensing (or for something else)
etc.
Presentation of Survey
Each group will give a presentation on their surveys in class. Every group member should take a part in presentation. The presentations should be in parallel with your report. You will have approximately 10-12 minutes for your presentation; we will have a discussion period of 5 minutes after the presentation. I will let you know the exact duration after the add-drop period.
The presentation content, its format and layout, and the way that you present it will affect your grade. The interest that your presentation attracts from the audience will also affect your grade.
Prepare your slides neatly and properly. It should contain at most 12 slides with reasonable content (only present the most important and interesting parts). Do not copy and paste any text / equation / table from a paper (if necessary, type them). If you need to use a figure (or an image) of a paper, take it but give a credit to this paper (so that we can understand how much effort you have put in preparing your presentation).
Project
You will also work in a group of two, with the same group-mate. You will have three options for the term project but your project topic must be aligned with your survey topic:
Choose a paper related to machine learning concepts. Then implement the algorithm proposed by this paper and also implement one of the compared algorithms used by this paper. Do not use any codes provided by the authors of the paper, or any other people, in case available. Run these two algorithms on the dataset you will select and compare their results using standard performance metrics, also using statistical tests. Additionally, follow a proper way of selecting the algorithms’ (hyper)parameters and also conduct parameter analysis. I expect you to select a recent paper that explains a not-so-straightforward algorithm.
Train and evaluate deep learning models for the dataset you will select. Here you may use the third-party codes, but you CANNOT select any dataset that was used to pretrain any of the deep learning models (e.g., you cannot use the ImageNet dataset to conduct your experiments). In this option, you are expected to get the model trained on your dataset and obtain reasonable test set performances. An important ingredient of this second option, is to explore the effects of different (hyper)parameters on the performance of the model. You need to select at least two different models (deep neural networks) and compare their results, using statistical tests. You are expected to select a not-so-easy dataset.
For the project, you are expected to select a paper for the first option, and a dataset for the second one on your own. The quality/difficulty of your work will affect your grade. You may contact me if you need my if you need feedback on your selection.
At the end, as a group, you will write a report (maximum of 6 pages). Give the details of the methodology you have followed and present your experimental results. The content of your report as well as its format, structure, and writing style will affect your grade. Similarly, do not copy and paste any text/equation/table from a paper (if necessary, type them). If you need to use a figure (or an image) of a paper, take it but give a credit to this paper. The reports are expected to be around 6 pages and must follow the IEEE two-column format as described in their templates. Try to follow the format as closely as possible. Both the content and the format will be subject to grading.
Presentation of Project
Each group will give a presentation on their project in class. Similar generic rules and expectations as those of the 'Presentation of Survey’ above apply to this presentation.
Deadlines
We follow no extension policy. Any course work turned in late will be penalised and will incur a reduction of 25% in the final score, for each day (or part thereof) it is late.
Sep. 29: Your group preference, if any
Oct. 13: Topic selection for the survey (as a group)
Oct. 26: Term project selection (as a group)
Nov. 10: Final report for the survey
Nov. 10 - 20: Survey Presentations (tentative)
Dec. 08 - 24: Project Presentations (tentative)
Dec. 24: Final report for the project
Late submissions policy
We follow no extension policy.
Any course work turned in late will be penalised and will incur a reduction of 25% in the final score, for each day (or part thereof) it is late.
Please make sure you fully understand the honor code as well as the code of discipline at Bilkent University and the Rules and Regulations of the Higher Education Council (YOK) (in Turkish). Cheating and plagiarism on exams, quizzes, and assignments will be punished according to these regulations.
GRADING POLICY
|