• Instructors
    • A. Ercument Cicek (Section I)
      • Office: EA514
      • E-mail: [lastname]
      • Office Hours: By appointment
    • Aysegul Dundar (Section II)
      • Office: EA412
      • E-mail: [first_initial][lastname]
      • Office Hours: By appointment
  • TAs
    • Ilayda Beyreli
      • E-mail: [firstname].[lastname]
      • Office: EA525
      • Office Hours: M 13:30 - 15:30
    • Hakan Sivuk
      • E-mail: [firstname][lastname]
      • Office: EA405
      • Office Hours: T 11:30 - 13:30
    • Sina Barazandeh
      • E-mail: [firstname].[lastname]
      • Office: EA525
      • Office Hours: F 12:30 - 14:30
  • Graders 
    • Halil Ibrahim Kuru
    • Burak Tasdemir
    • Said Fahri Altindis

    Location and Hours

    • Section 1
      • EE-214
      • T 13.30-15.20 (F2F) ; F 9:30-10:20 (F2F); Spare Hour: F 8:30-9:20 (F2F)
    • Section 2
      • EE-214
      • T 15.30-17.20 (F2F) ; F 11:30-12:20 (F2F); Spare Hour: F 10:30-11:20 (F2F)

    Grading Policy

    • Midterm (25%) - Nov 17, 2021, 17:30 - 20:00.  


                EB101: Sec 1 [Abbassi - Hannan]

                EB102: Sec 1 [Ismailoglu - Uyar]

                EB103: Sec1 [Unlusoy - Yilmaz] + Sec 2 [Abdul - Guliter]

                EB104: Sec2 [Gurkan - Senturk]

                EB204: Sec2 [Tarhan - Yuruten]

    • Final (30%) -  Jan 12, 2021, 18:00 - 20:00
    •       Classrooms: 

                  EB101: Sec 1 [Abbassi - Hannan]

                  EB102: Sec 1 [Ismailoglu - Uyar]

                  EB103: Sec1 [Unlusoy - Yilmaz] + Sec 2 [Abdul - Guliter]

                  EB104: Sec2 [Gurkan - Senturk]

                  EB204: Sec2 [Tarhan - Yuruten]

    • Three homework assignments, including programming ( HW1: 8% + HW2: 8% + HW3: 9% = 25%).
      • You can us any programming language for the first 2 homeworks. The third homework will be implemented with Python. There will be a simple tutorial on PyTorch and Jupyter, but basic Python knowledge is needed.
      • Tentative schedule for homework assignments are as follows: Week 3-4, Week 9-10, and Week 12-13.
    • One term project topic of your choice (20%)
      • Project proposal (5%)
      • Progress report and Demo (30%)
      • Final report and presentation (65%)
      • Personal Involvement and Peer Grades will affect your grade.
    • FZ Policy
      • This semester we will not assign FZ grades.

    • Late day: Any assignments turned in late will be penalized and will incur a reduction of 25% in the final score, for each day (or part thereof) it is late. We follow no extension policy.
    • Honor code: This course follows the Bilkent University Code of Academic Integrity, as explained in the Student Disciplinary Rules and Regulation. Violations of the rules will not be tolerated. Students may discuss and work on homework problems in groups. However, each student must write down the solutions independently, and without referring to written notes from the joint session. In other words, each student must understand the solution well enough in order to reconstruct it by him/herself. In addition, each student must write on the problem set the names of the people with whom s/he collaborated.



    We will have hands-on tutorials regarding using Google CoLab and Jupyter (Week 6) and using PyTorch on Google CoLab over Jupyter (Week 11).


    The purpose of the project is to increase your knowledge about machine learning and get hands on practical experience. Any project in the machine learning field that is feasible to accomplish in the given time can be proposed. You will work groups of 5 people. You can form groups only within your own section. The project can involve applying known methods to solve an interesting question, or it can also involve coming up with a new methodology to solve an existing problem on an existing data set. You are responsible of proposing the data and the algorithm. Not meeting the deadlines will be penalized.

    Group Formation: E-mail group members to your TA (Ilayda Beyreli). If you cannot find a group to join or you are looking for members email your TA (Ilayda Beyreli) and you will be teamed up with other by us. Your group will be assigned to a TA and you will interact with him or her directly for further. (Due: Oct 3, 2021, 5pm).

    Proposal Write Up: Maximum one page (single spaced) proposal write up. It should contain the following information: (1) project title, (2) team members, (3) description of the data, (4) precise description of the question you are trying to answer with the data, (5) what you plan to achieve by the milestone. You will receive written feedback from your TA. (Due: Oct 31, 2021, 5pm).

    Progress Report and Demo: You are expected to have some results by the progress date. At least three pages (single spaced). Include (i) a high quality introduction and background information, (ii) what have you done so far, you are expected to be in the implementation stage, (iii) what remains to be done and (iv) a clear description of the division of work among teammates. You will meet with your TA during the class hours and show your results with a 5-10 min demo/presentation. You will receive feedback from your TA.
    (Progress Report due:  Nov 28 , 2021, 5 pm; Demos will take place during class hours on Nov 30, 2021. Time slots are TBD.)

    Final Report You should submit a pdf file electronically. When submitting the final project report, also include your project presentation in PDF format. Also send an individual email to your project TA about peer grades for each of your teammates. The peer grades will be 0 to 5. 5 being the highest grade. The report should have the following format:

    1. Introduction: A quick summary of the problem, methods and results.
    2. Problem description: Detailed description of the problem. What question are you trying to address?
    3. Methods: Description of methods and datasets used.
    4. Results: The results of applying the methods to the data set. Include the list of questions your experiments are designed to answer Details of the experiments; observations.
    5. Discussion: Interpretation and discussion of the results.
    6. Conclusions: What is the answer to the question? What did you learn about the methods? Mention any future directions of interest.
    7. Appendix: A clear description of the contribution of each person. You may also include extra material (results, methods details) if needed in the appendix.

    (Final Report due: Dec 26, 2021, 5pm).

    Final Project Presentation: There will be a 10 minute in class final project presentation. Be prepared to answer questions not only what you have done but also on the details of the techniquesYou presentation has to be exactly 10 mins. You will lose points if you go over your time.
    (Presentations will take place during class hours on Dec 24, 2021 and Dec 28, 2021 exact schedule will be emailed).


    No required textbooks. Optional:

    • Christopher M. Bishop, Pattern Recognition and Machine Learning, Springer, 2011.
      Ethem Alpaydin, Introduction to Machine Learning, 2e. The MIT Press, 2010.
      Kevin P. Murphy, Machine Learning: a Probabilistic Perspective, The MIT Press, 2012.
      Tom Mitchell, Machine Learning, McGraw Hill, 1997.
    • Eli Stevens, Luca Antiga, Thomas Viehmann. Deep Learning with PyTorch. Manning Publications, 2020.

    Lecture Slides

    Will be posted on Moodle.

    The instructor reserves the right to make changes on the structure and the content of the course.