| Course Code | COMP9444 |
| Course Title | Neural Networks and Deep Learning |
| Convenor | Alan Blair |
| Admin | TBA |
| Classes | Wednesday 6-8pm and Thursday 2-4pm (weeks 1-5, 7-10) |
| Consultations | TBA |
| Units of Credit | 6 |
| Course Website | http://cse.unsw.edu.au/~cs9444/21T2/ |
| Handbook Entry | http://www.handbook.unsw.edu.au/postgraduate/courses/current/COMP9444.html |
This course aims to introduce students to the main topics and methods in the field of neural networks and deep learning, ranging from traditional neural network models to the latest research and applications of deep learning.
Topics chosen from: perceptrons, feedforward neural networks, backpropagation, deep convolutional networks for image processing; geometric analysis of trained neural networks; recurrent networks, language processing, semantic analysis, long short term memory; Hopfield networks, restricted Boltzmann machines and autoencoders, generative adversarial networks; deep reinforcement learning; designing successful applications of neural networks; recent developments in neural networks and deep learning.
After completing COMP9444, students should
The textbook for this course is:
Deep Learning
By Ian Goodfellow, Yoshua Bengio and Aaron Courville
MIT Press
http://www.deeplearningbook.org
https://mitpress.mit.edu/books/deep-learning
The course will assume knowledge of the following mathematical topics:
Students should study the relevant sections of the textbook (shown in brackets) and, if necessary, try to revise these topics on their own during the first few weeks of the course.
The planned topics for this course are:
| Week | Topic | Textbook |
|---|---|---|
| wk1 Wed | Neuroanatomy and Perceptrons | (1.2, 9.10) |
| wk1 Thu | Multi Layer Networks and Backpropagation | (4.3) |
| wk2 Wed | Probability, Generalisation and Overfitting | (3.1-14, 5.1-6, 7.11-12) |
| wk2 Thu | Cross Entropy, Softmax, Weight Decay, Momentum | (6.1-5) |
| wk3 Wed | PyTorch |
|
| wk3 Thu |
Hidden Unit Dynamics
|
(8.2-3) |
| wk4 Wed | Convolutional Networks | (7.9, 9.1-5) |
| wk4 Thu | Image Processing | (7.4, 8.4, 8.7.1) |
| wk5 Wed | Recurrent Networks | (10.2) |
| wk5 Thu | Long Short Term Memory | (10.7, 10.10) |
| wk6 | (Flexibility Week) | |
| wk7 Wed | Word Vectors | (12.4) |
| wk7 Thu |
Language Processing
|
(10.4)
|
| wk8 Wed |
Reinforcement Learning
|
(12.5.1.1)
|
| wk8 Thu |
Deep Reinforcement Learning
|
(18.1, 20.9)
|
| wk9 Wed |
Hopfield Networks & Boltzmann Machines
|
(16.7, 17.4, 18.2, 20.1-4)
|
| wk9 Thu |
Autoencoders
|
(14.1-5, 20.10.3)
|
| wk10 Wed |
Generative Adversarial Networks
|
(20.10.4) |
| wk10 Thu | Review |
The relevant sections of the textbook are shown in brackets.
The textbook may be supplemented with additional materials for some topics.
Due to social distancing restrictions, the course will be delivered online. Students are required to watch pre-recorded lecture videos before each session. The scheduled class time will take the form of an interactive video chat session, and will be used to briefly summarise the content, discuss recent developments, and to answer any questions that you may have about each topic.
We are planning to deliver all the course materials through
the course Ed page
. This includes course content (text, images and embedded videos) as well as exercises, quizzes, coding exercises (using jupyter notebooks), recordings of online sessions, assignments and on-line discussion.
WebCMS will be used only for group formation for Assignment 2.
The course materials, embedded videos and online sessions introduce you to the various concepts and methods, provide motivating examples to help you understand them, and demonstrate skills and processes. You should not expect to understand the material completely simply by watching the embedded videos. You should also:
The assessment for this course will be:
| Assignment 1 | 30% |
| Assignment 2 | 30% |
| Final Exam | 40% |
The assignments will involve writing code in PyTorch. Please try to install PyTorch on your own laptop. These are the versions of modules currently installed on the CSE lab machines.
| python3 | 3.7.3 |
| torch | 1.8.1 |
| numpy | 1.16.2 |
| sklearn | 0.20.2 |
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 course work. 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 on-line sources to help you understand what plagiarism is and how it is dealt with at UNSW:
Make sure that you read and understand these. 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
The pages below describe the policies and procedures in more detail:
You should also read the following page which describes your rights and responsibilities in the CSE context:
Every term, student feedback is requested in a survey using UNSW's myExperience online survey system where the feedback will be used to make improvements to the course. Students are also encouraged to provide informal feedback during the session, and to let course staff know of any problems as soon as they arise. Suggestions will be listened to openly, positively, constructively, and thankfully, and every reasonable effort will be made to address them.
Inspired by feedback from previous offerings, we have endeavoured to make the course content more accessible by expanding the dot points from the lecture slides into full paragraphs with images and clickable references, and editing the lecture recordings into short videos embedded below the corresponding text. We hope these changes will help to make this course a rewarding and enjoyable experience.
Resource created Monday 17 May 2021, 01:39:55 PM, last modified Saturday 12 June 2021, 07:19:35 AM.