Logo Students

COMP329 – Artificial Intelligence

2017 – S2 Day

General Information

Pdf icon Download as PDF
Unit convenor and teaching staff Unit convenor and teaching staff
Abhaya Nayak
Contact via Email
E6A 382
Wed 13:00 - 14:00 (or by appointment)
Rolf Schwitter
Contact via Email
E6A 333
Mon 13:00 - 14:00 (or by appointment)
Tutor
Sonit Singh
Contact via Email
Tutor
Akhtar Shermin
Contact via Email
Friday 10:00 - 11:00
Credit points Credit points
3
Prerequisites Prerequisites
(39cp at 100 level or above) including (COMP225 or COMP229 or COMP249)
Corequisites Corequisites
Co-badged status Co-badged status
Unit description Unit description
Artificial Intelligence (AI) is a well-established field that studies how computers and computer software capable of exhibiting intelligent behaviour can be designed. In this unit students will be exposed to fundamental concepts in AI such as agent architecture, knowledge representation, planning and search, as well as their application in some topical domains. Upon completion of this unit students will be able to apply problem-solving strategies that are required to build intelligent systems.

Important Academic Dates

Information about important academic dates including deadlines for withdrawing from units are available at http://students.mq.edu.au/student_admin/enrolmentguide/academicdates/

Learning Outcomes

  1. Describe the roles of various search techniques in AI and use appropriate tools to implement them.
  2. Build a simple conversational agent employing appropriate tools and AI techniques.
  3. Explain the evolutionary algorithms and their roles in AI, and implement some evolutionary algorithms in different contexts including adversarial games.
  4. Appreciate the role that uncertainty plays in AI, and demonstrate ability for sound reasoning of different sorts from uncertain knowledge.

General Assessment Information

 

​Assessment Tasks Submission/Completion Process

The assessment of this unit consists of four online tests, two assignments and a final exam. The four tests are online, and you will complete them on iLearn. You will submit the solutions to the two assignments via iLearn by the due date. The final examination is a closed book examination, and will be taken in person on the appropriate date. Note that students who are approved to sit a Supplementary Exam will be required to take it in the week of December 11 – 15.

Late Submission Policy

Late assignments (not online tests) will be accepted up to 48 hours after the submission deadline.There will be a deduction of 20% of the total available marks made from the total awarded mark for each 24 hour period or part thereof that the submission is late (for example, 25 hours late in submission – 40% penalty). This penalty does not apply for cases in which an application for special consideration is made and approved. In such cases, a compensating mechanism will be decided upon on a case by case basis.

Assessment Standards

COMP329 will be assessed and graded according to the University assessment and grading policies.

The following general standards of achievement will be used to assess each of the assessment tasks with respect to the letter grades. 

Pass: Can correctly reproduce facts and definitions across a breadth of concepts, but lacks depth of understanding. Can describe and/or employ search techniques in ways that are close to those discussed in lectures or notes. Can employ AI techniques to build a functioning conversational agent. Has basic understanding of evolutionary algorithms and adversarial games. Has demonstrated some ability for sound reasoning in an uncertain domain.

Credit/Distinction: As for Pass plus: Exhibits breadth and depth of understanding of concepts. Can proficiently describe and/or employ search techniques going beyond how they were discussed in lectures or notes. Can employ AI techniques to build very good conversational agents. Has excellent understanding of evolutionary algorithms and adversarial games, and can easily employ the former to develop strategies for the latter. Has excellent understanding of the role uncertainty plays in AI and demonstrated excellence for sound reasoning in uncertain domains.

High Distinction: As for Credit/Distinction plus: Is aware of the context in which the concepts are developed and their limitations. Can cogently describe in their own words and efficiently employ search techniques, going well  beyond how they were discussed in lectures or notes. Can employ AI techniques to build superb conversational agents. Has outstanding understanding of evolutionary algorithms and adversarial games, and can easily employ the former to develop and evaluate strategies for the latter. Has excellent understanding of the role uncertainty plays in AI and has outstanding ability for sound reasoning in uncertain domains.

Assessment Process

These assessment standards will be used to give a numeric mark to each assessment submission during marking. The mark will correspond to an appropriate letter grade when relevantly weighted. The final mark for the unit will be calculated by combining the marks for all assessment tasks according to the percentage weightings shown in the assessment summary.

Assessment Tasks

Name Weighting Due
Test 1 5% Week 3
Test 2 5% Week 6
Assignment 1 20% Week 8
Test 3 5% Week 9
Test 4 5% Week 12
Assignment 2 20% Week 12
Final Examination 40% TBA

Test 1

Due: Week 3
Weighting: 5%

This is an online test to give early feedback on students' ability to program and their understanding of basic search techniques.


This Assessment Task relates to the following Learning Outcomes:
  • Describe the roles of various search techniques in AI and use appropriate tools to implement them.

Test 2

Due: Week 6
Weighting: 5%

This test is meant to assess students' appreciation of conversational agents and natural language understanding.


This Assessment Task relates to the following Learning Outcomes:
  • Build a simple conversational agent employing appropriate tools and AI techniques.

Assignment 1

Due: Week 8
Weighting: 20%

The first assignment will require students to demonstrate their skills in (1)  building a conversational agent (a simple AI application), and  (2) programming in Python.


This Assessment Task relates to the following Learning Outcomes:
  • Build a simple conversational agent employing appropriate tools and AI techniques.

Test 3

Due: Week 9
Weighting: 5%

This test will assess students' understanding of search in adversarial games.


This Assessment Task relates to the following Learning Outcomes:
  • Describe the roles of various search techniques in AI and use appropriate tools to implement them.

Test 4

Due: Week 12
Weighting: 5%

This test will assess students' understanding of adversarial games as well as reasoning from uncertain knowledge.


This Assessment Task relates to the following Learning Outcomes:
  • Explain the evolutionary algorithms and their roles in AI, and implement some evolutionary algorithms in different contexts including adversarial games.
  • Appreciate the role that uncertainty plays in AI, and demonstrate ability for sound reasoning of different sorts from uncertain knowledge.

Assignment 2

Due: Week 12
Weighting: 20%

This assignment will require students to demonstrate their skills in (1) employing your knowledge of evolutionary algorithms to develop strategies for adversarial games, and  (2) programming in Python.


This Assessment Task relates to the following Learning Outcomes:
  • Explain the evolutionary algorithms and their roles in AI, and implement some evolutionary algorithms in different contexts including adversarial games.

Final Examination

Due: TBA
Weighting: 40%

The final examination will assess all the four learning outcomes. With regards to learning outcomes #1, #2 and #3, it allows to accurately assess the appreciation of good programming and problem solving skills. With regards to learning outcome #1, #3 and #4, it will assess students' understanding of fundamental concepts such as different types of search, games and  inferences.


This Assessment Task relates to the following Learning Outcomes:
  • Describe the roles of various search techniques in AI and use appropriate tools to implement them.
  • Build a simple conversational agent employing appropriate tools and AI techniques.
  • Explain the evolutionary algorithms and their roles in AI, and implement some evolutionary algorithms in different contexts including adversarial games.
  • Appreciate the role that uncertainty plays in AI, and demonstrate ability for sound reasoning of different sorts from uncertain knowledge.

Delivery and Resources

 

Classes

Each week you should attend three hours of lectures, a tutorial class and a practical session. For details of days, times and rooms consult the timetables webpage. Students are urged to actively participate in the tutorials; this helps enhancing the understanding by students.

Note that practicals and tutorials commence in week 2. You should have selected a practical session and a tutorial session during enrolment. You should attend the sessions you are enrolled in. 

 

Texts

There is no set textbook for the unit. The following are  recommended readings. Lecturers may  recommend other references.

S. Russell and P. Norvig. Artificial Intelligence: A Modern Approach, Prentice-Hall, 2009.

Poole, D. and Mackworth, AK.  Artificial Intelligence - Foundations of Computational Agents. Cambridge University Press 2017. (Available free of charge at: http://artint.info/2e/html/ArtInt2e.html under a Creative Commons Attribution-Noncommercial-No Derivative Works 2.5 Canada License.)

For some parts of learning, the necessary reading (book chapters, software documentation, papers, etc.) will be made available on iLearn.

 

Unit Webpage and Technology Used and Required

COMP329 uses iLearn for delivery of class materials, discussion boards, online tests, submission of assessment tasks and access to marks and comments. Students should check the iLearn site regularly for unit updates.

Questions that are of are of potential interest to other students in this unit, such as queries regarding the content of this unit, its tutorials or practicals, should be posted on discussion forum on iLearn. 

The practical work in this unit mostly involves programming in Python3, and will require some packages purpose packages relevant to AI. Instructions will be provided on how to use Python3 and these packages on the laboratory machines and how to download them for use on your own machines

Unit Schedule

Tentative Schedule

Week Topic Reading Material
1 Unit Organisation and Introduction Lecturer Supplied
2-3 Search in AI

Lecturer Supplied

3-4 Building a Conversational Agent Lecturer Supplied
5-6 Knowledge Representation and Reasoning Lecturer Supplied
7 Evolutionary Algorithms Lecturer Supplied
8-10 Adversarial Games and Multi-Agent Systems Lecturer Supplied
11-12 Uncertainty in AI Lecturer Supplied
13 Revision  

 

Policies and Procedures

Macquarie University policies and procedures are accessible from Policy Central. Students should be aware of the following policies in particular with regard to Learning and Teaching:

Academic Honesty Policy http://mq.edu.au/policy/docs/academic_honesty/policy.html

Assessment Policy http://mq.edu.au/policy/docs/assessment/policy_2016.html

Grade Appeal Policy http://mq.edu.au/policy/docs/gradeappeal/policy.html

Complaint Management Procedure for Students and Members of the Public http://www.mq.edu.au/policy/docs/complaint_management/procedure.html​

Disruption to Studies Policy http://www.mq.edu.au/policy/docs/disruption_studies/policy.html The Disruption to Studies Policy is effective from March 3 2014 and replaces the Special Consideration Policy.

In addition, a number of other policies can be found in the Learning and Teaching Category of Policy Central.

Student Code of Conduct

Macquarie University students have a responsibility to be familiar with the Student Code of Conduct: https://students.mq.edu.au/support/student_conduct/

Results

Results shown in iLearn, or released directly by your Unit Convenor, are not confirmed as they are subject to final approval by the University. Once approved, final results will be sent to your student email address and will be made available in eStudent. For more information visit ask.mq.edu.au.

Student Support

Macquarie University provides a range of support services for students. For details, visit http://students.mq.edu.au/support/

Learning Skills

Learning Skills (mq.edu.au/learningskills) provides academic writing resources and study strategies to improve your marks and take control of your study.

Student Enquiry Service

For all student enquiries, visit Student Connect at ask.mq.edu.au

Equity Support

Students with a disability are encouraged to contact the Disability Service who can provide appropriate help with any issues that arise during their studies.

IT Help

For help with University computer systems and technology, visit http://www.mq.edu.au/about_us/offices_and_units/information_technology/help/

When using the University's IT, you must adhere to the Acceptable Use of IT Resources Policy. The policy applies to all who connect to the MQ network including students.

Graduate Capabilities

Discipline Specific Knowledge and Skills

Our graduates will take with them the intellectual development, depth and breadth of knowledge, scholarly understanding, and specific subject content in their chosen fields to make them competent and confident in their subject or profession. They will be able to demonstrate, where relevant, professional technical competence and meet professional standards. They will be able to articulate the structure of knowledge of their discipline, be able to adapt discipline-specific knowledge to novel situations, and be able to contribute from their discipline to inter-disciplinary solutions to problems.

This graduate capability is supported by:

Learning outcomes

  • Describe the roles of various search techniques in AI and use appropriate tools to implement them.
  • Build a simple conversational agent employing appropriate tools and AI techniques.
  • Explain the evolutionary algorithms and their roles in AI, and implement some evolutionary algorithms in different contexts including adversarial games.
  • Appreciate the role that uncertainty plays in AI, and demonstrate ability for sound reasoning of different sorts from uncertain knowledge.

Assessment tasks

  • Test 1
  • Test 2
  • Assignment 1
  • Test 3
  • Test 4
  • Assignment 2
  • Final Examination

Problem Solving and Research Capability

Our graduates should be capable of researching; of analysing, and interpreting and assessing data and information in various forms; of drawing connections across fields of knowledge; and they should be able to relate their knowledge to complex situations at work or in the world, in order to diagnose and solve problems. We want them to have the confidence to take the initiative in doing so, within an awareness of their own limitations.

This graduate capability is supported by:

Learning outcomes

  • Describe the roles of various search techniques in AI and use appropriate tools to implement them.
  • Build a simple conversational agent employing appropriate tools and AI techniques.
  • Explain the evolutionary algorithms and their roles in AI, and implement some evolutionary algorithms in different contexts including adversarial games.
  • Appreciate the role that uncertainty plays in AI, and demonstrate ability for sound reasoning of different sorts from uncertain knowledge.

Assessment tasks

  • Test 1
  • Test 2
  • Assignment 1
  • Test 3
  • Test 4
  • Assignment 2
  • Final Examination

Creative and Innovative

Our graduates will also be capable of creative thinking and of creating knowledge. They will be imaginative and open to experience and capable of innovation at work and in the community. We want them to be engaged in applying their critical, creative thinking.

This graduate capability is supported by:

Learning outcomes

  • Build a simple conversational agent employing appropriate tools and AI techniques.
  • Explain the evolutionary algorithms and their roles in AI, and implement some evolutionary algorithms in different contexts including adversarial games.
  • Appreciate the role that uncertainty plays in AI, and demonstrate ability for sound reasoning of different sorts from uncertain knowledge.

Assessment tasks

  • Test 2
  • Assignment 1
  • Test 3
  • Test 4
  • Assignment 2

Critical, Analytical and Integrative Thinking

We want our graduates to be capable of reasoning, questioning and analysing, and to integrate and synthesise learning and knowledge from a range of sources and environments; to be able to critique constraints, assumptions and limitations; to be able to think independently and systemically in relation to scholarly activity, in the workplace, and in the world. We want them to have a level of scientific and information technology literacy.

This graduate capability is supported by:

Learning outcomes

  • Describe the roles of various search techniques in AI and use appropriate tools to implement them.
  • Build a simple conversational agent employing appropriate tools and AI techniques.
  • Explain the evolutionary algorithms and their roles in AI, and implement some evolutionary algorithms in different contexts including adversarial games.
  • Appreciate the role that uncertainty plays in AI, and demonstrate ability for sound reasoning of different sorts from uncertain knowledge.

Assessment tasks

  • Test 1
  • Test 2
  • Assignment 1
  • Test 3
  • Test 4
  • Assignment 2
  • Final Examination

Changes from Previous Offering

This unit has undergone substantive change. The earlier unit with code COMP329, named Knowledge Systems, was more geared towards Knowledge Representation and Reasoning, and used Prolog as the primary programming language. In the current offering the unit is named Artificial Intelligence. It covers a broader range of AI topics, with Python being used as the primary programming language. There are two major reasons for this change. (1) Since students in BIT (GDD) are required to complete either COMP329 or COMP347,  it was felt the content of COMP329 should be better aligned with the learning outcomes of the BIT (GDD) program. Furthermore, (2) many students to COMP329 come equipped with programming experience in procedural languages and find it difficult to switch to a declarative language like Prolog which calls for a very different way of thinking. 

Game playing needs search in a vast game trees in some form or other. It often involve making strategic moves with uncertain outcomes without knowing in advance the moves that the other players (adversaries) will make. The content of the unit is designed, by and large, keeping such issues in mind. However, the unit is not restricted to games. Other few topics such as conversational agents are covered so that the students will get an opportunity to appreciate some other aspects of AI.

In previous offerings, the assessment included a diagnostic test (10%), two assignments ( 20% each) and a final exam (50%). This offering has, instead, four online tests (5% each), two assignments (20% each) and a final exam (40%). Having the total assessment distributed across a larger number of tasks with more overlap of assessed knowledge and skills will allow assessment of the students' overall performance the unit with relatively less reliance on their performance in the final examination.