This is a foundation unit for the Intelligent Systems specialisation

Re-introduced as a Tier-2 unit (advanced unit) for Master of Information Technology - 2014

This unit serves as a Tier-2 (advanced) unit in the new Master of Information Technology course - 2014.

18/7/13 Amending unit and knowledge prerequisites, and reverting date of introduction of unit to the original date. Effective Semester 1 2014.

5/9/13 - Amended Role-Relevance of unit and Synopsis fields by removing reference to FIT5047 being a foundation unit for the Intelligent Systems Specialisation since no longer relevant. FIT5047 is a core unit in the 2014 MIT degree course structure.

21/10/2014 - Amended prerequisite requirements by adding 2015, FIT9xxx version of 2014, FIT5xxx foundation units. Approved at GPC 4/14 (Item 6.2).

10/07/2015 - Update objectives to learning outcomes for AQF compliance. Effective Sem 2, 2015.

21/7/2015 - updated learning outcomes as agreed by ADE, CE, and Discipline group. Effective S2-2o15

21/09/2016 - Admin: CE updated prerequisites to include new programming unit FIT9133.

09/06/2017 - Admin: Adding Reasons for Change. Updating exam hours from 3 to 2 hours as required by new University Examination procedures, effective S1 2018.

20/9/2019: Admin - updating exam duration to include additional 10 minutes as per University requirement.

1/10/19: Updating the unit name to Fundamentals of artificial intelligence. With the introduction of the Master of Artificial Intelligence and changes made to the Master of Data Science, it was agreed that the names of this unit would be changed and is already reflected in the 2020 courses. Effective semester 1, 2020.

11/11/2019: Prerequisite changes approved at FEC 5/19. Effective semester 1, 2020: removed disestablished units, added new foundation programming unit FIT9136, and added a prereq waiver for commencing C6007 MAI students. Effective semester 2, 2020: Replaced the statement "Fundamental math with introductory knowledge of probability" with unit MAT9004.

24/09/2020 Admin: Update to include new assessment and teaching approach fields as per Handbook requirements.

17/03/2021: Admin - updating Workload (in the correct location) to change laboratories to tutorials as per email from CE.

18/03/2021: Admin - following clarification from the Lecturer, the workload requirements have been updated to Lectures and Laboratories.

This unit introduces the main problems and approaches to designing intelligent software systems including: automated search methods; reasoning under uncertainty; planning; software agents; recommender systems; machine learning paradigms; natural language processing; user modelling and evolutionary algorithms.

This is one of the advanced units (Tier-2) in the Master of Information Technology - 2014, and is also available as an elective for all FIT masters.

At the completion of this unit students should be able to:

1. Explain the theoretical foundations of Artificial Intelligence (AI) - such as the Turing test, Rational Agency and the Frame Problem - that underpin the application to information technology and society.
2. Critically explain, evaluate and apply appropriate AI theories, models and/or techniques in practice - including logical inference, heuristic search, genetic algorithms, supervised and unsupervised machine learning and Bayesian inference.
3. Utilise appropriate software tools to develop AI models or software.
4. Utilise and explain evaluation criteria to measure the correctness and/or suitability of models.

020199

This unit introduces the main problems and approaches to designing intelligent software systems including automated search methods, knowledge representation and reasoning, planning, reasoning under uncertainty, machine learning paradigms, and evolutionary algorithms.

Prescribed text(s) Limited copies of prescribed texts are available for you to borrow in the library.

Russell, S and Norvig, P. (2010). Artificial Intelligence - A Modern Approach . (3rd Edition) Prentice-Hall.

Recommended resources

Witten, I. and Frank, E. (2005). Data Mining - Practical Machine Learning Tools and Techniques . (3rd Edition) Elsevier.

J. Hernandez-Orallo (2017), The measure of all minds. Cambridge University Press ( http://AllMinds.org ).

Jensen, F. V. (2007). Bayesian Networks and Decision Graphs . Springer-Verlag.

Korb, K and Nicholson, A. (2011). Bayesian Artificial Intelligence . (2nd Edition) CRC Press.

Technological requirements

Netica (free)

Weka Data Mining Toolkit (free)

Web access and internet access

On-campus and online

Lectures, tutorials and laboratories. This teaching and learning approach provides facilitated learning, practical exploration and peer learning. The tutorials address theoretical questions, and the laboratories are required to achieve practical experience in Bayesian networks and machine learning.

Examination (2 hours and 10 minutes): 60%; In-semester assessment: 40%

Because I have been asked to make this change in an email from Margot Schumacher (June 1, 2017):

Your unit FIT5047 requires update to the Examination component to satisfy the new Assessment in Coursework Units: Development and Implementation of an Assessment Regime Procedures, where an individual assessment task can be no more than 60%, and/or the new Assessment in Coursework Units: Examination procedures, where final exam will normally be 1.5 or 2 hours in duration. Longer exams (2.5 or 3 hours) require faculty education committee approval.

In response to an email from Margot Schumacher (17 February 2021) asking for the breakdown of assessment tasks.

1. Assessment Task 1: 20% - 10 quizzes (10%) and 2 small assignments at 5% each - ULO: 2,3,4
2. Assessment Task 2: 20% - BN and ML assignments at 10% each - ULO: 2,3,4
3. Examination 1: 60% - ULO: 1,2,4

Minimum total expected workload equals 12 hours per week comprising:

(a.) Contact hours for on-campus students:

(b.) Additional requirements (all students):

FIT

Callista prerequisites: No prerequisites for MBIS (Professional) (3341.2), MIT (2402.5), MIT Professional (3348.1), MIT (Professional) (2402.6), MIT (Honours) (3349), PGDIT (2411), PGCIT (2423) and MAI (C6007).

Callista & Handbook prerequisite units:

FIT9131 or FIT9133 or FIT9136) and fundamental math with introductory knowledge of probability; or entry into C6007.

From semester 2, 2020 onward: (FIT9131 or FIT9133 or FIT9136) and MAT9004; or entry into C6007.