COMP SCI 7318 - Deep Learning Fundamentals

North Terrace Campus - Semester 2 - 2020

This course introduces key concepts underlying the development of deep learning techniques. These include: the place of deep learning in the context of statistics and machine learning; the definition, training and validation of deep models. A range of common models and their applications will be presented. The foundational ideas presented in this course will equip students to understand and interpret future developments in this fast moving field.

Open All

Course Details

Course Code	COMP SCI 7318
Course	Deep Learning Fundamentals
Coordinating Unit	Computer Science
Term	Semester 2
Level	Postgraduate Coursework
Location/s	North Terrace Campus
Units	3
Contact	Up to 3 hours per week
Available for Study Abroad and Exchange	Y

Course Staff

Course Coordinator: Professor Javen Qinfeng Shi

Course Timetable

The full timetable of all activities for this course can be accessed from Course Planner.

Course Learning Outcomes

Students are expected to be familiar with programming in Python and Linear Algebra (matrix / vector multiplications), though we will cover some of that to flatten the learning curve.

Topics include:
Foundations of neural networks and deep learning
Techniques to improve neural networks: regularization and optimizations, hyperparameter tuning and deep learning frameworks;
Strategies to organize and successfully build a machine learning project;
Convolutional Neural Networks, its applications (object classification, object detection, face recognition, style transfer …) and related methods;
Recurrent Neural Networks, its applications (natural language processing, …) and related methods;

Optional Advanced topics may include:
Generative Adversarial Networks and Deep Reinforcement Learning;

We will also provide insights from the AI industry, from academia, and advice to pursue a career in AI.

University Graduate Attributes

This course will provide students with an opportunity to develop the Graduate Attribute(s) specified below:

University Graduate Attribute	Course Learning Outcome(s)
Deep discipline knowledge informed and infused by cutting edge research, scaffolded throughout their program of studies acquired from personal interaction with research active educators, from year 1 accredited or validated against national or international standards (for relevant programs)	1,2,3
Critical thinking and problem solving steeped in research methods and rigor based on empirical evidence and the scientific approach to knowledge development demonstrated through appropriate and relevant assessment	1,2,3
Teamwork and communication skills developed from, with, and via the SGDE honed through assessment and practice throughout the program of studies encouraged and valued in all aspects of learning	2,3
Career and leadership readiness technology savvy professional and, where relevant, fully accredited forward thinking and well informed tested and validated by work based experiences	1,2,3
Intercultural and ethical competency adept at operating in other cultures comfortable with different nationalities and social contexts able to determine and contribute to desirable social outcomes demonstrated by study abroad or with an understanding of indigenous knowledges	1,2,3
Self-awareness and emotional intelligence a capacity for self-reflection and a willingness to engage in self-appraisal open to objective and constructive feedback from supervisors and peers able to negotiate difficult social situations, defuse conflict and engage positively in purposeful debate	2

Learning Resources

Required Resources

No textbook required.
Knowing some basic statistics, probability, linear algebra and optimisation would be helpful, but not essential. They will be covered when needed.
Ability to program in Python or Matlab is required.

Online Learning

Our course forum is accessible via the Canvas.

Excellent external courses available online:
1. Learning from the data by Yaser Abu-Mostafa in Caltech.
2. Deep Learning courses by Andrew Ng in Stanford/coursera.
Learning & Teaching Activities

Learning & Teaching Modes

The course will be delivered through the following activities:

- Lectures
- Assignments
- Workshops

Lectures will introduce and motivate the basic concepts of each topic. Significant discussions and two-way communication are also expected during the lectures. The assignments will reinforce concepts by their application to problem solving. This will be done via programming work and mathmatical derivation. All material covered in the lectures and assignments are assessable.

Workshops are designed to demosrate more practical aspects (like Python&Pytorch toolbox) as well as selected popular specific neural networks architectures, designs and tricks.

Workload

The information below is provided as a guide to assist students in engaging appropriately with the course requirements.

This is a 3-unit course. Students are expected to spend about 8 hours per week on the course including a 2-hour lecture, 2-hour self study and up to 4 hours per week on completing assignments on average.

Tips for assignments
Start the assignment early. Do not leave it to the last week. Penalty applies to late assignment submissions that pass the announced deadlines.

Learning Activities Summary

No information currently available.

The University's policy on Assessment for Coursework Programs is based on the following four principles:

Assessment must encourage and reinforce learning.
Assessment must enable robust and fair judgements about student performance.
Assessment practices must be fair and equitable to students and give them the opportunity to demonstrate what they have learned.
Assessment must maintain academic standards.

Assessment Summary

The University's policy on Assessment for Coursework Programs is based on the following four principles:
Assessment must encourage and reinforce learning.
Assessment must enable robust and fair judgements about student performance.
Assessment practices must be fair and equitable to students and give them the opportunity to demonstrate what they have learned.
Assessment must maintain academic standards.
Assessment Summary

The course includes the following assessment components:
Final written exam at 55%.
Three assignments at 15% each.

Details

Component Weighting Learning Outcomes CBOK Areas
Assignments 15% each, 3 in total 1,2,3,4 1,2,3,4,6,7,8,9,10,11
Final Written Exam 55% 1,2,4 1,2,5,8

CBOK Legend

Abstraction
Design
Ethics
Interpersonal Communication
Societal Issues
History & Status of the Discipline
Hardware & Software
Data & Information
Programming
Human Computer Interfaces
Systems Development

Assessment Related Requirements

Hurdle Requirement: If your overall mark for the course is greater than 44 F, and your mark for the final written exam is less than 40%, your overall mark for the course will be reduced to 44 F.

Assessment Detail

Final written exam

This will be a 2-hour exam at the end of the course/semester. The exam will assess your knowledge and understanding of the course topics, as well as the abiliity to use the knowledge for problem solving. The exam is open-book. Books, lecture notes, slides print-out, calculators and paper dictionaries (English to foreign language) are permitted. The use of internet is not permitted.

Assignments

Each student is expected to complete assignments in the form of report and programming work. The assignments must be completed individually and all submissions are to be made under the declaration of following the academic honesty principles. Submissions will be subjected to plagiarism checks. This course has a zero-tolerance policy towards academic honesty violations. Offenders will be duly subjected to university procedures.

Submission

Assignment
Assignment solutions are to be submitted through Canvas.

No physical submissions of work will be accepted unless specifically requested by the lecturer.

Marks will be capped for late submissions, based on the following schedule:
1 day late – mark capped at 75%
2 days late – mark capped at 50%
3 days late – mark capped at 25%
more than 3 days late – no marks available.

Extensions to due dates will only be considered under exceptional medical or personal conditions and will not be granted on the last day due, or retrospectively. Applications for extensions must be made to the course coordinator by e-mail or hard copy and must include supporting documentation – medical certificate or letter from the student counselling service.

Examination
The examinations office will schedule the final exam. Students are expected to be available until after the supplementary examination period (precise dates are available from university calendar or exams office). No additional arrangments will be given if students are offered supplementary exams but are unable to attend.

Course Grading

Grades for your performance in this course will be awarded in accordance with the following scheme:

M10 (Coursework Mark Scheme)
Grade	Mark	Description
FNS		Fail No Submission
F	1-49	Fail
P	50-64	Pass
C	65-74	Credit
D	75-84	Distinction
HD	85-100	High Distinction
CN		Continuing
NFE		No Formal Examination
RP		Result Pending

Further details of the grades/results can be obtained from Examinations.

Grade Descriptors are available which provide a general guide to the standard of work that is expected at each grade level. More information at Assessment for Coursework Programs.

Final results for this course will be made available through Access Adelaide.

Student Feedback

The University places a high priority on approaches to learning and teaching that enhance the student experience. Feedback is sought from students in a variety of ways including on-going engagement with staff, the use of online discussion boards and the use of Student Experience of Learning and Teaching (SELT) surveys as well as GOS surveys and Program reviews.

SELTs are an important source of information to inform individual teaching practice, decisions about teaching duties, and course and program curriculum design. They enable the University to assess how effectively its learning environments and teaching practices facilitate student engagement and learning outcomes. Under the current SELT Policy (http://www.adelaide.edu.au/policies/101/) course SELTs are mandated and must be conducted at the conclusion of each term/semester/trimester for every course offering. Feedback on issues raised through course SELT surveys is made available to enrolled students through various resources (e.g. MyUni). In addition aggregated course SELT data is available.
Student Support
Policies & Guidelines
This section contains links to relevant assessment-related policies and guidelines - all university policies.
Fraud Awareness

Students are reminded that in order to maintain the academic integrity of all programs and courses, the university has a zero-tolerance approach to students offering money or significant value goods or services to any staff member who is involved in their teaching or assessment. Students offering lecturers or tutors or professional staff anything more than a small token of appreciation is totally unacceptable, in any circumstances. Staff members are obliged to report all such incidents to their supervisor/manager, who will refer them for action under the university's student’s disciplinary procedures.

The University of Adelaide is committed to regular reviews of the courses and programs it offers to students. The University of Adelaide therefore reserves the right to discontinue or vary programs and courses without notice. Please read the important information contained in the disclaimer.

Authorised by:	Deputy Vice-Chancellor and Vice-President (Academic)
Maintained by:	Course Outlines Administrator