COMPX525-23A (HAM)

Deep Learning

15 Points

Edit Header Content
Division of Health Engineering Computing & Science
School of Computing and Mathematical Sciences
Department of Computer Science

Staff

Edit Staff Content

Convenor(s)

Lecturer(s)

Administrator(s)

: maria.admiraal@waikato.ac.nz
: buddhika.subasinghe@waikato.ac.nz

Placement/WIL Coordinator(s)

Tutor(s)

Student Representative(s)

Lab Technician(s)

Librarian(s)

: alistair.lamb@waikato.ac.nz

You can contact staff by:

  • Calling +64 7 838 4466 select option 1, then enter the extension.
  • Extensions starting with 4, 5, 9 or 3 can also be direct dialled:
    • For extensions starting with 4: dial +64 7 838 extension.
    • For extensions starting with 5: dial +64 7 858 extension.
    • For extensions starting with 9: dial +64 7 837 extension.
    • For extensions starting with 3: dial +64 7 2620 + the last 3 digits of the extension e.g. 3123 = +64 7 262 0123.
Edit Staff Content

What this paper is about

Edit What this paper is about Content

This paper provides an introduction into Deep Learning, focussing on both algorithms and applications.

The learning outcomes for this paper are linked to Washington Accord graduate attributes WA1-WA11. Explanation of the graduate attributes can be found at: https://www.ieagreements.org/

Edit What this paper is about Content

How this paper will be taught

Edit How this paper will be taught Content
Reading all necessary chapters of the text book, and viewing of all recorded material is expected, as is participation in the lectures/Q+A sessions. You are responsible for being familiar with all material covered. Please read the relevant chapters *before* each lecture!
Edit How this paper will be taught Content

Required Readings

Edit Required Readings Content
Understanding Deep Learning, Simon J.D. Prince, MIT Press 2023, free draft @ https://udlbook.github.io/udlbook/
Edit Required Readings Content

You will need to have

Edit You will need to have Content
Contrary to what the definition of cheating says below, I am happy for you to use AI tools like ChatGPT, as long as you use them responsibly. Always double-check the correctness of any claim or statement .
Edit You will need to have Content

Learning Outcomes

Edit Learning Outcomes Content

Students who successfully complete the course should be able to:

  • Build a DL-based image classification from scratch (Assignment + Competition) [WA2, WA3, WA4, WA5, WA9]
    Linked to the following assessments:
    Programming assignment 1 (2)
    Programming Assignment 2 (3)
  • Demonstrate familiarity with the current mainstream Deep Learning algorithms (Test) [WA1, WA7]
    Linked to the following assessments:
    12 short Moodle quizzes (one every lecturing week) (1)
    Test (4)
  • Demonstrate good understanding of the basics of Deep Learning (Test) [WA1, WA7]
    Linked to the following assessments:
    12 short Moodle quizzes (one every lecturing week) (1)
    Test (4)
  • Employ and adapt pretrained models in DL applications (Assignment + Competition) [WA2, WA3, WA4, WA5, WA9]
    Linked to the following assessments:
    Programming assignment 1 (2)
    Programming Assignment 2 (3)
Edit Learning Outcomes Content
Edit Learning Outcomes Content

Assessments

Edit Assessments Content

How you will be assessed

Edit How you will be assessed Content

The assessment is based on the four components specified below.

If you are enrolled in a BE(Hons), samples of your work may be required as part of the Engineering New Zealand accreditation process for BE(Hons) degrees. Any samples taken will have the student name and ID redacted. If you do not want samples of your work collected then please email the engineering administrator, Natalie Shaw (natalie.shaw@waikato.ac.nz), to opt out.
Edit How you will be assessed Content

The internal assessment/exam ratio (as stated in the University Calendar) is 100:0. There is no final exam. The final exam makes up 0% of the overall mark.

The internal assessment/exam ratio (as stated in the University Calendar) is 100:0 or 0:0, whichever is more favourable for the student. The final exam makes up either 0% or 0% of the overall mark.

Component DescriptionDue Date TimePercentage of overall markSubmission MethodCompulsory
1. 12 short Moodle quizzes (one every lecturing week)
2 Jun 2023
No set time
24
  • Online: Submit through Moodle
2. Programming assignment 1
28 Apr 2023
No set time
25
  • Online: Submit through Moodle
3. Programming Assignment 2
2 Jun 2023
No set time
25
  • Online: Submit through Moodle
4. Test
6 Jun 2023
4:00 PM
26
  • Online: Submit through Moodle
Assessment Total:     100    
Failing to complete a compulsory assessment component of a paper will result in an IC grade
Edit Assessments Content