Skip to navigation | Skip to main content | Skip to footer
COMP14112: Artificial Intelligence Fundamentals

COMP14112: Artificial Intelligence Fundamentals

Academic Year 2017 - 2018, Semester 2

Note: this page is from an earlier year. Current information is on Blackboard.

Tim Morris

Tim Morris (course leader)
Room 2.107

Xiaojun Zeng

Xiaojun Zeng
Room G.7

Aims and objectives

This course introduces the study of Artificial Intelligence (AI) for students in all course streams. It is designed to stand alone as an introduction to AI, but also to provide a background for more advanced study. The course presents AI from a probabilistic viewpoint, and is centred around two specific problems: (i) robot localization; (ii) speech understanding. The lectures will present the main theoretical ideas needed to tackle these problems; the examples classes will re-inforce these through paper-and-pencil exercises, and the labs will involve the development of programs to solve them. There will be one hour of lectures and one hour of examples classes each week, as well as five two-hour lab sessions over the semester.

A student completing this course unit should:

  • Understand in broad outline the principal challenges of AI, the major research areas and the overall historical development of the subject.
  • Understand the fundamentals of probability theory, considered as an account of reasoning under uncertainty, and its central role in AI.
  • Understand in detail the problem of robot localization, and the methods used to solve it.
  • Understand in detail the problem of speech recognition, and the methods used to solve it.
  • Develop practical expertise in implementing probabilistic algorithms in AI.
  • Understand the philosophical foundations and limitations of probability theory in AI.


Course notes and copies of the lectures will be distributed. There is no textbook.


There is one lecture per week, Friday at 11am in Kilburn 1.1 The table gives the timetable for the course: dates, lecture titles and lecturer, and downloadable lecture notes, in "Large" format (one up) and "Small" format (two up), and Examples classes and Laboratory handouts. Examples classes solutions will follow. "Date" is the Monday of the week concerned.

Week Date Lecture topic and notes Who Lab / Coursework

1 A

1 Feb

A Very Brief Overview/Robot Localization I
Large Small


2 B

8 Feb

Robot Localization II
Large Small


Examples 1: Probability I
Examples 1: Solutions

3 A

15 Feb

Foundations of Probability
Large Small


Examples 2: Probability II
Examples 2: Solutions
Lab 1a: Robot Localization

4 B

22 Feb

Brief History of AI
Large Small


Examples 3: Probability III
Examples 3: Solutions

5 A

29 Feb

Introduction to Speech Recognition
Large Small


Examples 4: Turing's Paper
No solutions are provided
Lab 1b: Robot Localization

6 B

7 Mar

Building a Yes/No Classifier
Large Small


Examples 5: Speech Topics

7 A

14 Mar

Markov Chains
Large Small


Examples 6: Bayes' Classifier

Lab 2: Naive Bayes Classifier

Easter vacation


8 B

11 Apr

Hidden Markov Models
Large Small


Examples 7: Markov Models I

9 A

18 Apr

Putting It All Together
Large Small


Examples 8: Markov Models II

Lab 3: Hidden Markov Models

10 B

25 Apr

Robotics Revision
Large Small


Examples 9: Past Exam Paper (Section B)
Examples 9: Solutions

11 A

2 May

Speech Revision
Large Small


Examples 10: Past Exam Paper (Section A)
Examples 10: Solutions

12 B

9 May

Lab: Marking Catchup, Tuesday only

13 A

16 May

Lab: Marking Catchup, Monday only


Could not determine which HTML writer to use. Update the URL constants in DemonstratorConstants.php