Available in 2014

Callaghan Campus Semester 1

Previously offered in 2013, 2012, 2011, 2010, 2009, 2008, 2007, 2006, 2005, 2004

This course provides an overview about important past and current developments, concepts, and applications in the fast evolving field of machine intelligence. It is an introductory course and could later be extended by higher studies in areas such as, advanced machine learning, data mining, bioinformatics, image processing, optimisation, autonomous agents, computer vision, computer graphics, and related fields. The course's topic is a central part of computer science and software engineering. Many of the concepts addressed by this course were initially biologically motivated and fall under the umbrella of brain theory. The aim is to get an understanding of intelligence, learning, memory, language, and the workings of the human brain by modelling and implementing aspects of these concepts in the computer. With the availability of faster workstations and sophisticated robotic hardware machine intelligence methods can find more widespread applications. This course will address several applications and systems where machine intelligence methods lead to significant advancements, often surprising solutions, and sometimes triumphal success.

Objectives 1. Students to understand and apply Artificial Intelligence (AI) techniques;
2. Students to understand and implement examples of machine learning methods.
3. Students to obtain an overview of past and current developments in machine intelligence.
4. Students to develop the ability to project towards future developments of the field including possible ethical implications in areas such as data mining and robotics.
Content 1. Machine Learning
2. Automated Reasoning and Logic
3. Search and Prediction in Games
4. Neural Networks and Brain Mechanisms
5. Evolutionary Algorithms
6. Adaptive Robotics
Replacing Course(s) N/A
Transition N/A
Industrial Experience 0
Assumed Knowledge SENG1120, MATH1510 and MATH1110
Modes of Delivery Internal Mode
Teaching Methods Lecture
Laboratory
Assessment Items
Essays / Written Assignments As per course outline.
Examination: Formal As per the University's exam timetable.
Projects As per course outline.
Contact Hours Computer Lab: for 1 hour(s) per Week for Full Term
Lecture: for 3 hour(s) per Week for Full Term
Compulsory Components
Compulsory Course Component Students must obtain 40% in the final exam to pass the course.
Student achieving >25% but less that 40% will be offered an alternate assessment if, and only if, all other assessment items have been submitted.
Students obtaining <25% will not be offered an alternate assessment, and will fail the course, unless students have submitted Adverse Circumstances in accordance with the Adverse Circumstances Policy.
Timetables 2014 Course Timetables for COMP3330