COMP30030 Introduction to Artificial Intelligence

Academic Year 2020/2021

This module offers a very broad introduction to the fundamental concepts, and algorithms behind artificial intelligence, and aims to provide the student with the ability to apply some of the basic techniques used in Artificial Intelligence (AI). It also aims to introduce students to some of the AI Frameworks that are currently popular. Some of the module topics covered include: Knowledge Representation, Problem Solving & Search, Game Playing, Optimisation Problems, Planning, Machine Learning and Classification, Genetic Algorithms, Neural Networks & Deep Learning, Computer Vision and NLP, and Recommender Systems. Please note any student taking this module must have their own laptop. In addition, it is important that they can programme in Java, have a basic knowledge of Python, and have taken modules covering the following topics: data structures, propositional logic, algebra and calculus.

PLEASE NOTE: In light of the current Covid situation, some changes have been made to the syllabus and the way the content is delivered and assessed. This is especially important for any students repeating the module. These changes ensure that the lectures and assessment materials will be available online and any student who does not feel safe/comfortable attending campus will never be obliged to do so at any time (i.e., a student may complete this module remotely so long as they have access to the online content).

Show/hide contentOpenClose All

Curricular information is subject to change

Learning Outcomes:

By the end of this module a student should be able to:
(1) Explain the underlying principles, and evaluate the advantages and limitations, of the AI approach to problem solving.
(2) Describe and implement a range of search algorithms and discuss the limitations associated with each.
(3) Demonstrate an understanding of the application of artificial intelligence techniques to game playing.
(4) Define the concepts of different planning systems and explain how they differ from classical search techniques.
(5) Have a basic understanding of different machine learning approaches, neural networks and genetic algorithms.
(6) Understand the open challenges in the field of Human-Centered AI, can distinguish one recommendation approach from another and understand some of the current open challenges in this research area.
(7) Demonstrate that they have researched the module content beyond lectures.

Student Effort Hours: 
Student Effort Type Hours
Lectures

24
Practical

24
Autonomous Student Learning

60
Total

108
Approaches to Teaching and Learning:
Teaching and learning approaches include: active/task-based learning; lectures; lab work; 
Requirements, Exclusions and Recommendations
Learning Recommendations:

Students should have a solid knowledge of Data Structures and Algorithms and reasonable programming skills (pref Java).


Module Requisites and Incompatibles
Incompatibles:
IS10060 - Digital Technology


 
Assessment Strategy  
Description Timing Open Book Exam Component Scale Must Pass Component % of Final Grade
Class Test: Online Exam Unspecified n/a Graded No

10
Class Test: Online Exam Week 12 n/a Graded No

25
Continuous Assessment: Assignment Sheets & Implementation Tasks Varies over the Trimester n/a Graded No

50
Assignment: Flipped Classroom Assessment Unspecified n/a Graded No

15

Carry forward of passed components
Yes
 
Resit In Terminal Exam
Spring No
Please see Student Jargon Buster for more information about remediation types and timing. 
Feedback Strategy/Strategies

• Feedback individually to students, post-assessment
• Online automated feedback

How will my Feedback be Delivered?

Not yet recorded.