COMPSCI 760: Machine Learning
Hello, dear friend, you can consult us at any time if you have any questions, add WeChat: daixieit
COMPSCI 760: Machine Learning
Machine learning techniques are widely used in many computing applications; for example, in web search engines, spam filtering, speech and image recognition, computer games, machine vision, credit card fraud detection, stock market analysis and product marketing applications. Machine learning implies that there is some improvement that results from the learning program having seen some data. The improvement can be in terms of some performance program (e.g., learning an expert system or improving the performance of a planning or scheduling program), in terms of finding an unknown relation in the data (e.g., data mining, pattern analysis), or in terms of customizing adaptive systems (e.g., adaptive user-interfaces or adaptive agents).
This course is research oriented. The practical component involves working on a real-world like research project developed with the help of the teaching team. The research project involves definition of research questions, project planning, data analysis workflow, programming, collaboration effort and regular communication of project progress in a oral or written form, including writing a literature review and a final research report. Programming skills are necessary for this course. The practical component of the course expects group work.
Lectures will introduce some of the recent developments in the field of machine learning. Students are expected to attend the lectures as they will be evaluated about their content in the final exam. Although this class is research oriented, students should be aware that the final exam weights significantly (50%) on the final grade.
Course Requirements
Prerequisite: CS361 or CS762
Lectures topics
Week 1-7: Introduction, Advanced Neural Networks
Week 8-12: Fairness in Machine Learning, Adversarial Learning
Learning Outcomes
The students will be able to:
Discuss the idea that all machine learning algorithms have a basis and will be able to describe the basis of several algorithms
Discuss the theory that for a particular dataset one algorithm will perform well and for another
dataset a different algorithm will perform well. There is no one algorithm that performs well on all datasets.
Independently develop and carry out to completion a research project addressing real-world
problems using appropriate machine learning methodology and open-source datasets in a group of preferably 5 students.
Design a good set of experiments for determining the answer to some basic research question,
such that they can show that the experiments actually support the question they are asking. Assessments
Your final grade will consist of a number of assignment marks worth 40% combined and an exam worth 60%. This is a research based course, so the assignment marks will be based on a research project work, performed in a collaboration with fellow students.
There is a practical and a theoretical pass on this paper. To pass the course, students must pass both the Practical component (Assignments) and the Theory component (Exam) separately, as well as obtaining 50% in their overall final mark. This means you need to have more than 50% of the exam marks and 50% of the marks for the assignments. Hence make sure you allocate enough time for both the practical assessments and exam preparation.
We use the standard university grade boundaries. >89.5 for A+, then 5 mark increments down to >49.5 for C-.
You can find a list of assignments and the timeline for the semester here: () . We strongly advise students to have a look a this document at the beginning of the semester to get an idea of what types of assignment are given along the semester.
Workload Expectations
This course is a 15 point course and students are expected to spend about 150 hours in total. Expected weekly workload (excluding the teaching break): 1 hour lecture, 1 hour lecture review, 1-2 hour reading and thinking, and 6-7 hours for the research project/assignments.
Students are expected to spend additional 30 hours for assessment (e.g. exam, presentation) preparation.
Teaching Staff
Thomas Lacombe (lecturer, course coordinator)
Room: 419, Computer Science Building (Building 303)
Email: thomas.lacombe@auckland.ac.nz (mailto:thomas.lacombe@auckland.ac.nz)
Office hours: Only by appointment; For many matters where the issue is generally applicable to other students, you may be best advised to go through a class representative.
Katerina Taskova (lecturer - second part of the semester)
Room: 493, Computer Science Building (Building 303S)
Email: katerina.taskova@auckland.ac.nz (mailto:katerina.taskova@auckland.ac.nz) Office hours: TBA during mid-term break
Katharina Dost (tutor/marker)
Email: kdos481@aucklanduni.ac.nz (mailto:kdos481@aucklanduni.ac.nz)
Lecture Times and Schedule
Day and time |
Room |
Monday 10:00AM - 11:00AM |
Architecture - West, Room 301 |
Wednesday 11:00AM - 12:00PM |
Architecture - West, Room 301 |
Thursday 10:00AM - 11:00AM |
Architecture - West, Room 301 |
Tentative schedule for lectures and presentations*:
Week |
Mon |
Wed |
Thu |
1 (18/07) |
Intro lecture |
Lecture |
Lecture |
2 (25/07) |
Pitching ideas |
Pitching ideas |
Pitching ideas |
3 (01/08) |
Lecture |
Lecture |
Presentation 1 |
4 (08/08) |
Presentation 1 |
Presentation 1 |
Presentation 1 |
5 (15/08) |
Lecture |
Lecture |
Presentation 2 |
6 (22/08) |
Presentation 2 |
Presentation 2 |
Presentation 2 |
break (29/08) |
|
|
|
break (05/09) |
|
|
|
7 (12/09) |
Lecture |
Q&A Part 1 |
Lecture |
8 (19/09) |
Lecture |
Lecture |
Lecture |
9 (26/09) |
Presentation 3 |
Presentation 3 |
Presentation 3 |
10 (03/10) |
Presentation 3 |
Lecture |
Lecture |
11 (10/10) |
Presentation 4 |
Presentation 4 |
Presentation 4 |
12 (17/10) |
Presentation 4 |
Q&A Part 2 |
Review/Q&A |
* This may vary depending on the numbers of research group projects and due to the nature of the practical component. We will inform you as soon as timeslots are fixed or if anything changes during the semester.
Zoom link for lectures and presentations: https://auckland.zoom.us/j/99513913023? pwd=QTNSb0UzcHUvb290MjdrQlkwMHFEUT09 (https://auckland.zoom.us/j/99513913023? pwd=QTNSb0UzcHUvb290MjdrQlkwMHFEUT09)
Class reps
The class rep for this semester is Davy Yang (xyan289@aucklanduni.ac.nz
(mailto:xyan289@aucklanduni.ac.nz) ).
Class reps can act as an intermediary between students in the class and the lecturers and tutors. You can share with them any suggestions/complaints/remarks about the lectures. The class reps are not a part of the teaching team.
Seeking Assistance
The primary source of assistance is the teaching staff. Please contact us with any questions or concerns about the course. We all are available via email. For help with more generic study skills or literacy, the Student Learning Centre and Library both offer many courses designed to help students become more efficient at study.
Piazza
We have set up Piazza for this course. The main purpose of Piazza is for you to interact with other students in the course; while lecturers will monitor Piazza and help if necessary, we believe that the best way for Piazza to work in this class is if you are all collectively responding to each other's problems!
To encourage student responses, we as lecturers will follow a "24 hour" rule: during the first 24 hours of any post about the material in this course, we will not respond. (Note: this does not mean that we will respond immediately after 24 hours! Depending on when your question goes up, we may be in meetings, or it may be after work hours and we're trying to take care of our families, etc. In general we'll get responses up as soon as is reasonable. If you haven't seen a response in two working days, please repost or email us.)
In addition, we reserve the right to remove posts what we feel are detrimental to the class. Please bear in mind that Piazza posts are not anonymous to the lecturing staff.
Exam
The final exam is worth 50% of your final mark. Please check Student Services Online (SSO) for the exam time and date. The exam is will be designed and conducted as online, non-invigilated, time- limited examination. Provisional exam results can be obtained from SSO.
You will get your final grade via SSO. Please also do understand that we are not allowed to be in communication with you in regards to your exam after the exam is written. If you email any of us during this period regarding the exam we won't be able to respond to your email.
If you would like to know more about exams process please see
exams/final-results.html (https://www.auckland.ac.nz/en/students/academic-information/exams- and-final-results/after-exams/final-results.html)
If you feel you need to talk to a person about the exam results, we suggest the science student center or the student adviser relevant to your degree.
people.html (https://www.auckland.ac.nz/en/science/about-the-faculty/school-of-computer- science/our-people.html)
Missed Exam
If you miss the exam for any valid reason, or you sit the exam but believe that your performance was impaired for some reason, then you may be able to apply for an aegrotat, compassionate or special pass consideration. For more detailed information, contact the science student center.
Course Expectations
The document linked below outlines the School of Computer Science's philosophy of learning and teaching and our expectations for student engagement. Please read it carefully!
Academic Integrity
Sharing assignment solutions and source code does not help learning. Consequently, our academic integrity policy does not permit sharing of solutions or source code leading to solutions. Violation of this will result in your assignment submission attracting no marks, and you may face disciplinary actions in addition. Therefore, please do not share assignments, assignment solutions and/or source code leading to assignment solutions. Do not publish or make your assignments or solutions available in any form online, or you will be liable if someone copies your solution. Please come talk to us if you have any doubt over what is legit and what is not. You can refer to online tutorials and resources. However, please learn from them and implement the solutions yourself based on what you've learnt from those sources. Do not blindly copy from online sources. If there is a real need to copy some code snippet, please ensure (a) you understand what the code snippet does, and (b) cite the source in a comment directly above the snippet. Don't leave your computers, devices, and belongings unattended — you must secure these at all times to prevent anyone having access to your assignments or solutions.
Inclusive Learning
All students are asked to discuss any impairment related requirements privately, face to face and/or in written form with the course coordinator, lecturer or tutor.
Student Disability Services also provides support for students with a wide range of impairments, both visible and invisible, to succeed and excel at the University. For more information and contact details, please visit the Student Disability Services’ website at http://disability.auckland.ac.nz ()
If your ability to complete assessed coursework is affected by illness or other personal circumstances outside of your control, contact a member of teaching staff as soon as possible before the assessment is due.
If your personal circumstances significantly affect your performance, or preparation, for an exam or eligible written test, refer to the University’s aegrotat or compassionate consideration
page: https://www.auckland.ac.nz/en/students/academic-information/exams-and-final- results/during-exams/aegrotat-and-compassionate-consideration.html ( exams/aegrotat-and-compassionate-consideration.html)
This should be done as soon as possible and no later than seven days after the affected test or exam date.
Student Charter and Responsibilities
The Student Charter assumes and acknowledges that students are active participants in the learning process and that they have responsibilities to the institution and the international community of scholars. The University expects that students will act at all times in a way that demonstrates respect for the rights of other students and staff so that the learning environment is both safe and productive. For further information visit Student Charter (https://www.auckland.ac.nz/en/students/forms- policies-and-guidelines/student-policies-and-guidelines/student-charter.html ( guidelines/student-charter.html) ).
2022-07-22