Module Details |
The information contained in this module specification was correct at the time of publication but may be subject to change, either during the session because of unforeseen circumstances, or following review of the module at the end of the session. Queries about the module should be directed to the member of staff with responsibility for the module. |
Title | Computational Intelligence | ||
Code | COMP575 | ||
Coordinator |
Dr JYI Goulermas Computer Science J.Y.Goulermas@liverpool.ac.uk |
||
Year | CATS Level | Semester | CATS Value |
Session 2016-17 | Level 7 FHEQ | Second Semester | 15 |
Aims |
|
Understand the basic structures and the learning mechanisms underlying neural networks within the field of artificial intelligence and examine how synaptic adaptation can facilitate learning and how input to output mapping can be performed by neural networks. Obtain an overview of linear, nonlinear, separable and non separable classification as well as supervised and unsupervised mapping. Understand the benefit of adopting naturally inspired techniques to implement optimisation of complex systems and acquire the fundamental knowledge in various evolutionary techniques. Bec ome familiar with the basic concepts of systems optimisation and its role in natural and biological systems and entities. |
Learning Outcomes |
|
Learning the advantages and main characteristics of neural networks in relation to traditional methodologies. Also, familiarity with different neural networks structures and their learning mechanisms. |
|
Appreciation of the advantages of evolutionary-related approaches for optimisation problems and their advantages compared to traditional methodologies. Also, understanding the different techniques of evolutionary optimisation for discrete and continuous configurations |
|
Understanding of the needs for genetic encoding and modelling for solving optimisation problems and familiarisation with the evolutionary operators and their performance. |
|
Understanding of the neural network learning processes and their most popular types, as well as appreciation of how neural networks can be applied to artificial intelligence problems. |
Syllabus |
|
1 |
For Neural Networks (part I), 12 lectures delivering the following chapters:
For Evolutionary Computation (part II), 12 lectures delivering the following chapters:
|
Teaching and Learning Strategies |
|
Lecture - Part 1: Neural Networks (12) and Part 2: Evolutionary Computation (12) |
|
Tutorial - Slide Presentation and Blackboard |
Teaching Schedule |
Lectures | Seminars | Tutorials | Lab Practicals | Fieldwork Placement | Other | TOTAL | |
Study Hours |
24 Part 1: Neural Networks (12) and Part 2: Evolutionary Computation (12) |
12 Slide Presentation and Blackboard |
36 | ||||
Timetable (if known) | |||||||
Private Study | 114 | ||||||
TOTAL HOURS | 150 |
Assessment |
||||||
EXAM | Duration | Timing (Semester) |
% of final mark |
Resit/resubmission opportunity |
Penalty for late submission |
Notes |
Unseen Written Exam | 180 | Semester 2 Exam period | 100 | Yes | Standard UoL penalty applies | Exam Notes (applying to all assessments) - none |
CONTINUOUS | Duration | Timing (Semester) |
% of final mark |
Resit/resubmission opportunity |
Penalty for late submission |
Notes |
Recommended Texts |
|
Reading lists are managed at readinglists.liverpool.ac.uk. Click here to access the reading lists for this module. Explanation of Reading List: |