Module Database Search



MODULE DESCRIPTOR
Module Title
Advanced Artificial Intelligence
Reference CM4107 Version 1
Created April 2017 SCQF Level SCQF 10
Approved August 2017 SCQF Points 15
Amended ECTS Points 7.5

Aims of Module
To introduce students to the state-of-the-art Artificial Intelligence, including machine learning and neural networks. A particular focus will be late-breaking techniques in Deep Learning.

Learning Outcomes for Module
On completion of this module, students are expected to be able to:
1 Explain and analyse techniques used for neural and deep learning.
2 Implement key algorithms, critically evaluate Artificial Intelligence solutions and appraise ethical issues.
3 Describe variety of methods and technologies developed for Artificial Intelligence that can be applied to real-world problems.
4 Apply the methods and techniques used in machine learning and logics.
5 Critically examine and evaluate relevant literature in artificial intelligence.

Indicative Module Content
Fundamentals of Natural and Artificial Logic; Reasoning and Inferring Searching and Planning; Computational Game Theory; Artificial Intelligence heuristics; Programming for Games; Probabilistic Bayesian Inference; Machine Learning Algorithms; Swarm Intelligence and Multi-Agent Systems; Neural and Bio-Inspired Intelligence; Problem Solving in Artificial Intelligence; Knowledge-based Artificial Intelligence; Real-World Applications of Artificial Intelligence; Deep Learning;

Module Delivery
Key concepts are introduced and illustrated through lectures and directed reading. The understanding of students is tested and further enhanced through interactive tutorials. In the laboratories, the student will progress through a sequence of exercises to develop sufficient knowledge and skills in Artificial Intelligence.

Indicative Student Workload Full Time Part Time
Contact Hours 33 N/A
Non-Contact Hours 117 N/A
Placement/Work-Based Learning Experience [Notional] Hours N/A N/A
TOTAL 150 N/A
Actual Placement hours for professional, statutory or regulatory body    

ASSESSMENT PLAN
If a major/minor model is used and box is ticked, % weightings below are indicative only.
Component 1
Type: Coursework Weighting: 100% Outcomes Assessed: 1, 2, 3, 4, 5
Description: Practical work worth 100%

MODULE PERFORMANCE DESCRIPTOR
Explanatory Text
The student must achieve a D in C1.
Module Grade Minimum Requirements to achieve Module Grade:
A The student must achieve an A in C1.
B The student must achieve a B in C1.
C The student must achieve a C in C1.
D The student must achieve a D in C1.
E The student must achieve an E in C1.
F The student must achieve an F in C1.
NS Non-submission of work by published deadline or non-attendance for examination

Module Requirements
Prerequisites for Module None.
Corequisites for module None.
Precluded Modules None.

INDICATIVE BIBLIOGRAPHY
1 Russell and Norvig. Artificial Intelligence: A Modern Approach.
2 Raschka. Python Machine Learning. Packt
3 N D LEWIS, 2016, Deep Learning Step by Step with Python
4 RASHID T, 2016, Make Your Own Neural Network, CreateSpace Publishing
5 BISHOP C, 2006 , Pattern Recognition and Machine Learning, Springer
6 KOWALSKI R, 2011, Computational Logic and Human Thinking, Cambridge University Press.
7 ERTEL W, 2011, Introduction to Artificial Intelligence, Springer

Robert Gordon University, Garthdee House, Aberdeen, AB10 7QB, Scotland, UK: a Scottish charity, registration No. SC013781