¾«¶«´«Ã½app

USQ Logo
The current and official versions of the course specifications are available on the web at .
Please consult the web for updates that may occur during the year.

CSC8003 Machine Learning

Semester 2, 2020 On-campus Toowoomba
Short Description: Machine Learning
Units : 1
Faculty or Section : Faculty of Health, Engineering and Sciences
School or Department : School of Sciences
Student contribution band : Band 2
ASCED code : 020199 - Computer Science not elsewhere
Grading basis : Graded

Staffing

Examiner:

Requisites

Pre-requisite: (STA2300 or STA8170) and CSC1401 or equivalent program and statistical knowledge and skills.

Rationale

One of the most common tasks performed by data scientists and data analysts is machine learning for prediction. This introductory course gives an overview of machine learning including concepts, techniques, and algorithms. The course will give students the basic ideas and intuition behind modern machine learning methods as well as a bit more formal understanding of how, why, and when they work. The underlying theme in the course is statistical inference as it provides the foundation for most of the methods covered. The course aims at giving a graduate-level student a thorough grounding in the methodologies, technologies, mathematics and algorithms currently needed by people for research in data science or practices in data analytics.

Synopsis

Machine learning is the science of getting computer programs to self-improve performance through experiences. In the past decade, machine learning has given us face and speech recognition, recommender systems for music or movies, self-driving cars, effective web search, and a vastly improved understanding of the human genome. Machine learning is so pervasive today that people probably use it dozens of times a day without knowing it. In this course, students will learn about the most effective machine learning techniques from a variety of perspectives. Students will also gain practice implementing the machine learning techniques and getting them to work for problem solving. More importantly, students will learn about not only the theoretical underpinnings of learning, but also gain the practical know-how to quickly and powerfully apply these techniques to new problems.

Objectives

On successful completion of this course students should be able to:

  1. Analyse data using supervised machine learning models and estimate the performance
  2. Analyse data using unsupervised machine learning models and estimate the performance
  3. Evaluate the situational requirements of various machine learning applications and justify the appropriate choice of machine learning model
  4. Given various constraints, optimize a given machine learning model
  5. Develop a complex model, based on multiple machine learning algorithms, which gives accurate and robust predictions

Topics

Description Weighting(%)
1. Machine learning concepts and performance estimation 10.00
2. Supervised learning (Linear/nonlinear algorithms, decision trees, support vector machines, neural networks)
35.00
3. Unsupervised learning (clustering, dimensionality reduction, deep learning) 25.00
4. Semi-supervised learning 8.00
5. Collaborative filtering and recommendations 8.00
6. Cyber security and other machine learning applications, ethic 14.00

Text and materials required to be purchased or accessed

ALL textbooks and materials available to be purchased can be sourced from (unless otherwise stated). (https://omnia.usq.edu.au/textbooks/?year=2020&sem=02&subject1=CSC8003)

Please for alternative purchase options from USQ Bookshop. (https://omnia.usq.edu.au/info/contact/)

Battiti, R and Brunato, M 2017, The LION way: Machine Learning plus Intelligent Optimization, Version 3.0 edn, LIONlab, ¾«¶«´«Ã½app of Trento, Italy,
<>.
(Note: PDF version available from .)

Reference materials

Reference materials are materials that, if accessed by students, may improve their knowledge and understanding of the material in the course and enrich their learning experience.
Berman, J 2013, Principles of Big Data: Preparing, Sharing, and Analyzing Complex Information, Morgan Kaufmann.
Bishop, CM 2006, Pattern Recognition and Machine Learning.
Dean, J 2014, Big Data, Data Mining, and Machine Learning: Value Creation for Business Leaders and Practitioners, Wiley.
Duda, R., Hart, P. and Stork, D 2000, Pattern Classification, 2nd edn.
Goodfellow, I., Bengio, Y., Courville, A., and Bengio, Y 2016, Deep Learning, Vol. 1, MIT Press.
Mitchell, TM 1997, Machine Learning, McGraw Hill.
Segaran, T 2007, Programming Collective Intelligence: Building Smart Web 2.0 Applications, O'Reilly Media Inc.
Witten, I, Frank, E and Hall, M 2017, Data Mining: Practical Machine Learning Tools and Techniques, 4th edn, Elsevier.
(Held as eBook.)
Access to computer and internet facilities for computer programming and assignment submission. The Student Edition of Matlab, Manual and CD, Prentice-Hall.

Student workload expectations

Activity Hours
Assessments 58.00
Directed ¾«¶«´«Ã½app 52.00
Private ¾«¶«´«Ã½app 55.00

Assessment details

Description Marks out of Wtg (%) Due Date Objectives Assessed Notes
ASSIGNMENT 1 100 20 17 Aug 2020 1,3,4
ASSIGNMENT 2 100 30 07 Sep 2020 2,3,4
PROJECT 100 50 26 Oct 2020 1,2,3,4,5

Important assessment information

  1. Attendance requirements:
    There are no attendance requirements for this course. However, it is the students’ responsibility to study all material provided to them or required to be accessed by them to maximise their chance of meeting the objectives of the course and to be informed of course-related activities and administration.

  2. Requirements for students to complete each assessment item satisfactorily:
    To satisfactorily complete an individual assessment item a student must achieve at least 50% of the marks for that item.

  3. Penalties for late submission of required work:
    Students should refer to the Assessment Procedure (point 4.2.4)

  4. Requirements for student to be awarded a passing grade in the course:
    To be assured of receiving a passing grade a student must achieve at least 50% of the total weighted marks available for the course.

  5. Method used to combine assessment results to attain final grade:
    The final grades for students will be assigned on the basis of the aggregate of the weighted marks obtained for each of the summative items for the course.

  6. Examination information:
    There is no examination in this course.

  7. Examination period when Deferred/Supplementary examinations will be held:
    There is no examination in this course. There will be no deferred or supplementary examinations.

  8. ¾«¶«´«Ã½app Student Policies:
    Students should read the USQ policies: Definitions, Assessment and Student Academic Misconduct to avoid actions which might contravene ¾«¶«´«Ã½app policies and practices. These policies can be found at .

Evaluation and benchmarking

In meeting the ¾«¶«´«Ã½app’s aims to establish quality learning and teaching for all programs, this course monitors and ensures quality assurance and improvements in at least two ways. This course:
1. conforms to the USQ Policy on Evaluation of Teaching, Courses and Programs to ensure ongoing monitoring and systematic improvement.
2. forms part of the Master of Science Program and is benchmarked against the internal USQ accreditation/reaccreditation processes which include (i) stringent standards in the independent accreditation of its academic programs, (ii) close integration between business and academic planning, and (iii) regular and rigorous review.

Other requirements

  1. Computer, e-mail and Internet access:
    Students are required to have access to a personal computer, e-mail capabilities and Internet access to UConnect. Current details of computer requirements can be found at .

  2. Students can expect that questions in assessment items in this course may draw upon knowledge and skills that they can reasonably be expected to have acquired before enrolling in this course. This includes knowledge contained in pre-requisite courses and appropriate communication, information literacy, analytical, critical thinking, problem solving or numeracy skills. Students who do not possess such knowledge and skills should not expect the same grades as those students who do possess them.

Date printed 6 November 2020