Subject Descriptions - Subject Information


Calendar: 2017 Postgraduate
Faculty: Faculty of Engineering and Information Sciences
Department: School of Computing and Information Technology


Subject Information
Subject Code CSCI933
Subject Name Machine Learning Algorithms and Applications
Credit Points 6
Pre-Requisites None.
Co-Requisites None.
Restrictions None.
Equivalence INFO433, INFO933
Assessment 3 assignments plus final examination.
General Subject Yes.
EFTSL (Non Weighted) 0.125
Non Weighted Student Contribution Amounts
Commonwealth Supported (HECS) Students Only
Pre-1997 Pre-2005 Post-2005 Post-2008 Post-2009 Post-2010
$ 1131  $ 1131  $ 1131  $ 1131  $ 1131  $ 1131 
Weighted Student Contribution Amounts  
Work Experience No
Tutorial Enrolment Information No tutorials for this subject

Subject Availability
Session Autumn  (27-02-2017 to 22-06-2017)
Campus Wollongong
Delivery Method On Campus
Instance Name Class 1
Course Restrictions No restrictions
Contact Hours 2 hour lecture
Lecturer(s) and
Cons. times
Philip Ogunbona
Coordinator(s) and
Cons. times
Philip Ogunbona
Instance Comment  
Census Date 31-03-2017

Subject Availability
Session CCNU Session 1 2017/2018  (18-09-2017 to 07-01-2018)
Campus Central China Normal University Wuhan
Delivery Method On Campus
Instance Name Class 1
Course Restrictions No restrictions
Contact Hours  
Lecturer(s) and
Cons. times
Guangyou Zhou
Coordinator(s) and
Cons. times
Fenghui Ren
Luping Zhou
Philip Ogunbona
Instance Comment  
Census Date 10-10-2017

Subject Description
Machine learning aims to develop computer systems that learn from example data to model and solve real-life problems. Students will develop the knowledge and skills required to analyse, design and implement machine learning systems applicable in big data analytics, social media data analysis, computer vision, neuroimage analysis, speech recognition, surveillance, information retrieval, bioinformatics, document image analysis and recognition, computational linguistics, forensics and biometrics. Conceptual understanding of the fundamental tools and their application in practice will be emphasised. Topics covered include supervised and unsupervised learning; kernel machines; deep learning; data clustering; Bayesian methods; linear discriminant analysis; regression; and graphical models.


Subject Learning Outcomes
On successful completion of this subject, students will be able to:
1. Describe and use data clustering and discriminant analysis in classification.
2. Use Bayesian methods in pattern analysis and recognition
3. Use learning methods in pattern analysis and recognition
4. Design and implement simple application systems based on pattern analysis and recognition.

Extra Information
Generic Extra Information:
Assumed Knowledge: Knowledge that would be gained during the course of a Bachelor degree in Computer Science or Bachelor degree in a cognate mathematical or information sciences.

Textbook Information

Text book information is available via the UniShop website:



Search Criteria [Click here for help]
Subject Code / Name
Level
Department
Session
Campus
Delivery Method
General Subjects