Module Specification

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.
1. Module Title Machine Learning and BioInspired Optimisation
2. Module Code COMP532
3. Year Session 2023-24
4. Originating Department Computer Science
5. Faculty Fac of Science & Engineering
6. Semester Second Semester
7. CATS Level Level 7 FHEQ
8. CATS Value 15
9. Member of staff with responsibility for the module
Dr M Fang Computer Science Meng.Fang@liverpool.ac.uk
10. Module Moderator
11. Other Contributing Departments  
12. Other Staff Teaching on this Module
Mrs J Birtall School of Electrical Engineering, Electronics and Computer Science Judith.Birtall@liverpool.ac.uk
13. Board of Studies
14. Mode of Delivery
15. Location Main Liverpool City Campus
    Lectures Seminars Tutorials Lab Practicals Fieldwork Placement Other TOTAL
16. Study Hours 30

        10

40
17.

Private Study

110
18.

TOTAL HOURS

150
 
    Lectures Seminars Tutorials Lab Practicals Fieldwork Placement Other
19. Timetable (if known)            
 
20. Pre-requisites before taking this module (other modules and/or general educational/academic requirements):

COMP517 Programming Fundamentals
21. Modules for which this module is a pre-requisite:

 
22. Co-requisite modules:

 
23. Linked Modules:

 
24. Programme(s) (including Year of Study) to which this module is available on a mandatory basis:

25. Programme(s) (including Year of Study) to which this module is available on a required basis:

26. Programme(s) (including Year of Study) to which this module is available on an optional basis:

27. Aims
 

In this module we focus on learning agents that interact with an initially unknown world. Since the world is dynamic this module will put strong emphasis on learning to deal with sequential data unlike many other machine learning courses. The aims can be summarised as:
To introduce and give an overview to state of the art bio-inspired self-adapting methods. 
To enable students to not only learn to build models with reactive input/output mappings but also build computer programs that sense and perceive their environment, plan, and make optimal decisions. 
To familiarise students with multi-agent reinforcement learning, swarm intelligence, deep neural networks, evolutionary game theory, artificial immune systems and DNA computing.
To demonstrate principles of bio-inspired methods, provide indicative examples, develop problem-solving abilities and provide students with experience to apply the learnt methods in real-world problems.

 
28. Learning Outcomes
 

(LO1) A systematic understanding of bio-inspired algorithms that can be used for autonomous agent design and complex optimisation problems.

 

(LO2) In depth insight in  the mathematics of biologically inspired machine learning and optimisation methods.

 

(LO3) A comprehensive understanding of the benefits and drawbacks of the various methods.

 

(LO4) Demonstrate knowledge of using the methods in real-world applications (e.g. logistic problems).

 

(LO5) Practical assignments will lead to hands on experience using tools as well as coding of own algorithms.

 
29. Teaching and Learning Strategies
 

Teaching Method 1 - lectures
Description: students will be expected to attend three hours of formal lectures in a typical week
Attendance Recorded: Yes

Teaching Method 2 - tutorials
Description: one hour of weekly seminar given by students in groups, or one hour of tutorial by instructor.
Attendance Recorded: Yes

Standard on-campus delivery
Teaching Method 1 - Lecture
Description: Mix of on-campus/on-line synchronous/asynchronous sessions
Teaching Method 2 - Tutorial
Description: On-campus synchronous sessions

 
30. Syllabus
   

This module will cover the following topics: Introduction to parallel problem solving from nature/overview (2 lectures) Reinforcement Learning/multi-agent reinforcement learning/replicator dynamics (8 lectures) Swarm Intelligence: Ant System, Ant Colony Optimization/Bee System/Swarm Robotics (6 lectures) Deep Learning: Restricted Boltzman Machines/auto-encoder networks/deep belief networks (8 lectures) Artificial immune systems (4 lectures) DNA computing (2 lectures) Lecture slides and reading material will be made available to the students.

 
31. Recommended Texts
  Reading lists are managed at readinglists.liverpool.ac.uk. Click here to access the reading lists for this module.
 

Assessment

32. EXAM Duration Timing
(Semester)
% of
final
mark
Resit/resubmission
opportunity
Penalty for late
submission
Notes
  (532) Written Examination There is a resit opportunity. Standard UoL penalty applies for late submission. This is not an anonymous assessment. Assessment Schedule (When) :2 120 70
33. CONTINUOUS Duration Timing
(Semester)
% of
final
mark
Resit/resubmission
opportunity
Penalty for late
submission
Notes
  (532.2) Report 2 There is a resit opportunity. Standard UoL penalty applies for late submission. This is not an anonymous assessment. Assessment Schedule (When) :2 0 15
  (532.1) Report 1 There is a resit opportunity. Standard UoL penalty applies for late submission. This is not an anonymous assessment. Assessment Schedule (When) :2 0 15