Course Title: Artificial Intelligence

Part A: Course Overview

Course Title: Artificial Intelligence

Credit Points: 12.00

Terms

Course Code

Campus

Career

School

Learning Mode

Teaching Period(s)

COSC1125

City Campus

Postgraduate

140H Computer Science & Information Technology

Face-to-Face

Sem 1 2006,
Sem 1 2007,
Sem 1 2008,
Sem 1 2009,
Sem 1 2010,
Sem 1 2011,
Sem 1 2012,
Sem 1 2013,
Sem 1 2014,
Sem 1 2015,
Sem 1 2016

COSC1125

City Campus

Postgraduate

171H School of Science

Face-to-Face

Sem 1 2017,
Sem 1 2018,
Sem 1 2019,
Sem 2 2020,
Sem 2 2021

COSC1126

Bundoora Campus

Undergraduate

140H Computer Science & Information Technology

Face-to-Face

Sem 1 2006

COSC1127

City Campus

Undergraduate

140H Computer Science & Information Technology

Face-to-Face

Sem 1 2006,
Sem 1 2007,
Sem 1 2008,
Sem 1 2009,
Sem 1 2010,
Sem 1 2011,
Sem 1 2012,
Sem 1 2013,
Sem 1 2014,
Sem 1 2015,
Sem 1 2016,
Sem 2 2016

COSC1127

City Campus

Undergraduate

171H School of Science

Face-to-Face

Sem 1 2017,
Sem 1 2018,
Sem 1 2019,
Sem 2 2020,
Sem 2 2021

COSC2240

Taylors College KL

Undergraduate

140H Computer Science & Information Technology

Face-to-Face

Offsh 1 11

Course Coordinator: Prof. Sebastian Sardina

Course Coordinator Phone: +61 3 9925 9824

Course Coordinator Email: sebastian.sardina@rmit.edu.au

Course Coordinator Location: 14.08.7D

Course Coordinator Availability: By appointment.


Pre-requisite Courses and Assumed Knowledge and Capabilities

You may not enrol in this course unless it is explicitly listed in your enrolment program summary.

Enforced Prerequisite: COSC1285/2123 Algorithms and Analysis

In addition, you should have basic knowledge of algorithms, programming, mathematics.

  


Course Description

This course introduces you to the basic concepts and techniques of Artificial Intelligence (AI). AI is the sub-area of computer science devoted to creating software and hardware to get computers to do things that would be considered ‘intelligent’ as if people did them. Artificial intelligence has had an active and exciting history and is now a reasonably mature area of computer science. Many of the research discoveries have now reached the point of industrial application and. many companies have made and saved millions of dollars by exploiting the results of AI research. However the goal of emulating human intelligence has not been reached and many stimulating and challenging problems remain.

All serious programmers and software engineers should know about the major AI techniques, which are regarded by many the core knowledge of any Computer Science degree. This course will allow you to gain generic problem solving skills that have applicability to a wide range of real-world problems. Topics covered include search strategies for solving problems, knowledge representation, automated planning, intelligent agents, reasoning under uncertainty, bio-inspired optimisation, and machine learning.


Objectives/Learning Outcomes/Capability Development

-


Course Learning Outcomes

Upon successful completion of this course you should be able to:

  • CLO 1: describe the key components of the artificial intelligence (AI) field and its relation and role in Computer Science;
  • CLO 2: identify and describe artificial intelligence techniques, including search heuristics, knowledge representation, automated planning and agent systems, machine learning, and probabilistic reasoning;
  • CLO 3: identify and apply AI techniques to a wide range of problems, including complex problem solving via search, knowledge-base systems, machine learning, probabilistic models, agent decision making, etc.;
  • CLO 4: design and implement appropriate AI solution techniques for such problems;
  • CLO 5: analyse and understand the computational trade-offs involved in applying different AI techniques and models.
  • CLO 6: Communicate clearly and effectively using the technical language of the field correctly.


Overview of Learning Activities

The learning activities included in this course are:

  • Lectorials, where key AI concepts and syllabus material will be presented and put in context, and targeted exercise and quizzes will be given to solve and discuss interactively during the session;
  • Reading material and online videos covering the syllabus material will be made available for students to process, usually before the corresponding lectorial; and
  • workshops/tutorials/labs/group discussions (including online forums) focused on projects and problem solving will provide practice in the application of AI theory and procedures, allow exploration of concepts with teaching staff and other students, and give feedback on your progress and understanding.

A total of 120 hours of study is expected during this course, comprising:

Teacher-directed hours (48 hours): Lectorials will take place once a week to introduce concepts and motivations and showcase and discuss targeted problems interactively. You will work on set problems each week in tutorials and find practical programming support in labs. Online discussions among students and teaching staff will be held in the course forum. Regular online quizzes, assignments, forum interaction, and/ or practical projects will provide regular feedback on progress. 

Student-directed hours (72 hours): You are expected to be self-directed, studying independently outside class to consolidate your understanding of the theory and practice.


Overview of Learning Resources

The course is supported by online tools, such as the Canvas learning management system and/or Google-based systems, which provide specific learning resources. See the RMIT Library Guide at http://rmit.libguides.com/compsci


Overview of Assessment


Assessment tasks

 

Assessment Component 1: Assignments

Weighting 15%

This assessment task supports CLOs 3, 4, & 5


Assessment Component 2: Take Home Exercises

Weighting 40%

This assessment task supports CLOs 1, 2, 3, 5, 6


Assessment Component 3: Project

Weighting 45%

This assessment task supports CLOs 1, 2, 3, 5, 6

This course has no hurdle requirements. Please note that the breadth and depth of assessment tasks for postgraduate students will be greater than the tasks for undergraduate students.