Machine learning is the algorithmic approach to learning from data. The course also covers aspects of data mining, the application of machine learning to obtain insight from data. In this course machine learning algorithms are placed in the context of their theoretical foundations in order to understand their derivation and correct application. Machine learning also is an empirical science, where performance of algorithms must be rigorously evaluated on datasets. Completion of this course will contribute to further learning in advanced topics such as deep learning, bioinformatics, computer vision, and robotics. Topics covered in the course include: linear models for regression and classification, local methods (nearest neighbour), tree learning, kernel machines, neural networks, unsupervised learning, ensemble learning, and learning theory. To expand and extend the development of theory and algorithms presented in lectures, practical examples will be given in tutorials and programming tasks during the project.

This course aims to expose students to the theory, algorithms and empirical work that are essential inter-dependent components of machine learning. In particular, the assignments are aimed at giving students an opportunity for active learning via practical experience in applying machine learning to real applications. The second assignment has a broad scope and should be treated as a small-scale project with submission of software and a written report. COMP9417 forms part of a suite of AI courses that together comprise the Artificial Intelligence major in the undergraduate computer science programs and the postgraduate information technology program.

Before commencing this course, students should have completed the pre-requisite courses (or equivalent) and ensure they have acquired knowledge in the relevant areas:

• Mathematical assumed knowledge is the completion of basic university mathematics courses, such as the UNSW courses MATH1131 and MATH1231 (e.g. be familiar with vector calculus and linear algebra, or be willing to learn them independently).
• Additionally, in practice, some knowledge of basic probability, statistics (e.g. MATH2801, and the listed excluded equivalents MATH2089, MATH2099, MATH2859, MATH2901, BEES2041, ECON3209, CVEN2002), and logic will be the starting point for some course materials (e.g., as in a typical university course on discrete mathematics).
• Be able to program well in Python or be willing to learn it independently.

The delivery of this course is multimodal, with in-person/live-streaming lectures and in-person/online tutorials. All course materials can be found on the course Moodle page. 

Student Conduct

The Student Code of Conduct (Information, Policy) sets out what the University expects from students as members of the UNSW community. As well as the learning, teaching and research environment, the University aims to provide an environment that enables students to achieve their full potential and to provide an experience consistent with the University's values and guiding principles. A condition of enrolment is that students inform themselves of the University's rules and policies affecting them, and conduct themselves accordingly.

In particular, students have the responsibility to observe standards of equity and respect in dealing with every member of the University community. This applies to all activities on UNSW premises and all external activities related to study and research. This includes behaviour in person as well as behaviour on social media, for example, Facebook groups set up for the purpose of discussing UNSW courses or coursework. Behaviour that is considered in breach of the Student Code Policy as discriminatory, sexually inappropriate, bullying, harassing, invading another's privacy or causing any person to fear for their personal safety is serious misconduct and can lead to severe penalties, including suspension or exclusion from UNSW.

If you have any concerns, you may raise them with your lecturer or approach the School Ethics Officer, Grievance Officer, or one of the student representatives.

Plagiarism is defined as using the words or ideas of others and presenting them as your own. UNSW and CSE treat plagiarism as academic misconduct, which means that it carries penalties as severe as being excluded from further study at UNSW. There are several online sources to help you understand what plagiarism is and how it is dealt with at UNSW:

• Plagiarism and Academic Integrity
• UNSW Plagiarism Procedure

Make sure that you read and understand these resources. Ignorance is not accepted as an excuse for plagiarism. In particular, you are also responsible that your assignment files are not accessible by anyone but you by setting the correct permissions in your CSE directory and code repository, if using. Note also that plagiarism includes paying or asking another person to do a piece of work for you and then submitting it as your own work.

UNSW has an ongoing commitment to fostering a culture of learning informed by academic integrity. All UNSW staff and students have a responsibility to adhere to this principle of academic integrity. Plagiarism undermines academic integrity and is not tolerated at UNSW. Plagiarism at UNSW is defined as using the words or ideas of others and passing them off as your own.

If you haven't done so yet, please take the time to read the full text of

• UNSW's policy regarding academic honesty and plagiarism

The pages below describe the policies and procedures in more detail:

• Student Code Policy
• Student Misconduct Procedure
• Plagiarism Policy Statement
• Plagiarism Procedure

You should also read the following page which describes your rights and responsibilities in the CSE context:

• Essential Advice for CSE Students

All assessment work items (except maybe for the final exam) will involve electronic submission via the Moodle page. Details of submission, deadlines, late penalties, etc., will be in the specifications.

The overall course mark will be the sum of the marks for the course components.

The requirement to pass the course is to acquire a minimum mark of 50 out of 100.

Week       Lecture                                  Tutorial                                Assignment                         Other

1               Regression                            No tutorial                             -                                        -

2               Classification                        Regression                            -                                        - 

3               Classification                        Classification                        -                                        - 

4               Tree Learning                        Classification                       Homework 1 due              Project Group Formation due

5               Kernel Methods                     Tree Learning                       -                                         - 

6               Flexibility Week                     Flexibility Week                    -                                         - 

7               Ensemble Learning               Kernel Methods                  Homework 2 due             -  

8               Neural Network                     Ensemble Learning              -                                        - 

9               Unsupervised Learning         Neural Network                   -                                        -  

10             Learning Theory                    Unsupervised Learning       -                                        Group Project due

Owing to the expansion of machine learning in recent years, and the wide availability of online materials, it is no longer possible to recommend a single textbook for this course. However, below is a list of books (those with an asterisk have copies freely available online) that can be consulted to back up and expand on the course content. If you plan to continue with machine learning, any of these (and many others) are worth reading:

• Hastie, T., Tibshirani, R. and Friedman, J. The Elements of Statistical Learning: Data Mining, Inference, and Prediction. * Springer, 2009.
• James, G., Witten, D., Hastie, T., and Tibshirani, R. An Introduction to Statistical Learning with Applications in R . * Springer, 2017.
• Flach, P. Machine learning: The Art and Science of Algorithms that Make Sense of Data. Cambridge University Press, 2012.
• Rogers, S. and Girolami, M. A First Course in Machine Learning (2nd Edition) . Chapman and Hall/CRC, 2016.
• Bishop, C. Pattern recognition and Machine Learning. Springer, 2006.
• Charniak, E. Introduction to Deep Learning . MIT Press, 2019.
• Blum, A., Hopcroft, J. and Kannan, R. Foundations of Data Science .* 2018.
• Shalev-Shwartz, S. and Ben-David, S. Understanding Machine Learning: From Theory to Algorithms . Cambridge University Press, 2014.
• Deisenroth. M. P., Faisal, A. A., and Ong, C. S., Mathematics for Machine Learning. *Cambridge University Press, 2020.
• Geron, A. Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow, 2nd Edition . O'Reilly Media, Inc, 2019.

Other resources (e.g. links to online documentation) will be made available in the relevant course materials.

This course is evaluated each session using myExperience.

Following the previous offerings of this course, students requested increasing homework weights to be proportional to the amount of effort going into it. Therefore, we have increased the homework's weight to address this feedback since the last offering. Students also asked that tutors explain the material rather than Q&A sessions, which we will implement in this offering. Students found the weekly assignments very time-consuming, therefore in this offering, we will not have weekly assignments.