Author Dr Jim Smith
Institution University of the West of England, Bristol
Module Title Introduction to Artificial Intelligence
Module Homepage n/a
Original Resource www.cems.uwe.ac.uk/exist/shortmodspec.xql?moduleCode=UFCE3H-20-1 (as found on 2/2/10)
Programme of study BSc Computer Science, BSc Computing, BSc. Robotics, BSc. Games Technology
Academic Level 1st Year
Credit Value 20
Rationale Students are introduced to the basic paradigms of "traditional" and "computational" Artificial Intelligence as tools for automated problem solving.
Aims Students will be taught the following:

1. Introduction to Artificial Intelligence
2. Knowledge Representation
3. Artificial Neural Networks Natural and artificial networks.
4. Evolutionary Algorithms
5. Collective Intelligence Swarm Intelligence & Robot Societies
Benefits The materials below consist of lecture notes, tutorial plans, reading materials and links to further online resources.
They also include a series of weekly self-assessment tests in xml format exported from Blackboard version 9.
In general the tutorials consist of group activities, which in practice are usually documented and mediated online via discussion boards etc. within a VLE.
More individual, self-directed work is typically provided by :
(i) staff suggestions for extensions of the work carried out in tutorials - very much in response to how they have run.
(ii) Directed reading and other multimedia links provided
(iii) The provision of weekly tests for formative self-assessment. These are provided to promote access to a wider community of learners, by providing the means for them to assess, in their own time, how well they have understood each weeks materials.
Student response, and staff monitoring, has shown that these resources were heavily used particularly as revision aids.
The benefits were increased attendance, retention, and pass-rates.
Date of use 2005-2009
Download module The module can be downloaded as a zip file at the following URL: http://open.jorum.ac.uk/xmlui/handle/123456789/1559
Accessibility If you wish to view the material in alternative formats, then you may wish to access the software tools collated by TechDis and available at http://www.techdis.ac.uk/getaccessapps (as found on 2/2/10)
Topic

Elements
Introduction to Problem Solving as Search

Lecture: Introduction to Machine Learning
Lecture: What is Artificial Intelligence?
Lecture: Using AI: Learning as Search.
Lecture: Search Strategies.
Lecture: Informed Search Strategies
Tutorial: tutorial Week1
Tutorial: tutorial Week1 : Staff Notes
Tutorial: Week2 tutorial
Tutorial: Scenarios for tutorial
Tutorial: Tutorial Week 4: Search.
Example: Jugs-fsm
Test: Intro to AI week 1 introduction test
Test: Intro to AI week 2 test Turing Searle etc
Test: Intro to AI week 3 problem solving as search
Test: Intro to AI week 4 - uninformed search strategies
Test: Intro to AI week 5 - heuristic search strategies
Topic

Elements
Knowledge Representation

Lecture: Knowledge representation 1
Lecture: Knowledge representation 2
Lecture: Knowledge representation 3
Lecture: Knowledge representation 4
Lecture: Knowledge representation 5
Lecture: Knowledge representation 5 - additional notes
Practical: Practical 1 Worksheet
Practical: Einstein practical
Practical: Practical 1 for teachers
Practical: Practical 1 - draft 5
Practical: Practical 1 - answers
Practical: Knowledge representation - practical 2
Practical: practical 2 for teachers
Practical: practical 3
Practical: practical 3 for teachers
Practical: practical 4
Practical: practical 4 for teachers
Practical: practical 5
Practical: practical 5 for teachers
Reading Material: Semantic Web
Reading Material: Semantic Web 1
Reading Material: Semantic Web 2
Notes: Knowledge Representation expanded notes
Notes: Knowledge Representation Final notes
Notes: Knowledge Representation teachers notes
Test: KR - week 1
Test: KR - week 2
Test: KR - week 3
Test: KR - week 4
Test: KR - week 5
Topic

Elements
Neural Networks

Lecture: Neural Networks 1
Lecture: Neural Networks 2
Lecture: Neural Networks 3
Lecture: Neural Networks 4
Reading Material: Neural Net Resources
Reading Material: Neural Networks Handout lecture 1
Reading Material: Neural Networks Handout lecture 1 extended
Reading Material: Neural Networks Handout Lecture 2
Reading Material: Neural Networks Handout Lecture 2 extended
Reading Material: Neural Networks Handout Lecture 3
Reading Material: Neural Networks Lecture 3 extended
Reading Material: Neural Networks Handout Lecture 4
Reading Material: Neural Networks Handout Lecture 4 extended
Practical: Neural Networks Handout Practical 2
Practical: Neural Networks Handout Practical 2 for teachers
Practical: Neural Networks Handout Practical 3
Practical: Neural Networks Handout Practical 4
Viewing Material: Background Reading video
Test: Neural Networks - week 1
Test: Neural Networks - week 2
Test: Neural Networks - week 3
Test: Neural Networks - week 4
Topic

Elements
Evolutionary Computing

Lecture: What is an Evolutionary Algorithm? The SGA
Lecture: Genetic Algorithms
Lecture: GeneticProgramming
Tutorial: Algorithms Tutorial One: The Human GA
Tutorial: Tutorial : EC week 2
Tutorial: EC tutorial week 3
Test: Evolutionary Computation test 1 The need for heuristics and the SGA
Test: Evolutionary Computation test 2 Operators and Representations
Test: Evolutionary Computation test 3 Genetic Programming
Topic

Elements
Swarm Intelligence

Lecture: Swarm Intelligence: problem solving with emergent phenomena
Tutorial: Ants Tutorial
Tutorial: Swarm Tutorial
Topic

Elements
Intros and revision lectures

Lecture: Introduction to Artificial Intelligence - overall revision session
Lecture: Introduction to A.I. - Introductory Lecture
Reading material: Learning as search
Reading Material: Random Processes