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 | INTELLIGENT SYSTEMS | ||
Code | CKIT533 | ||
Coordinator |
Dr F Grasso Computer Science Floriana@liverpool.ac.uk |
||
Year | CATS Level | Semester | CATS Value |
Session 2018-19 | Level 7 FHEQ | Whole Session | 15 |
Aims |
|
1. To provide students with a comprehensive understanding of intelligent systems techniques. 2. To enable students to evaluate modern techniques of artificial intelligence and machine learning for intelligent system projects. 3. To provide students with the knowledge and skills required to develop and deploy expert systems and artificial intelligent tools. |
Learning Outcomes |
|
An ability to analyse and evaluate intelligent systems techniques. |
|
A comprehensive understanding of the differences between intelligent system applications and conventional computer applications. |
|
A critical ability to deploy appropriate software tools and skills for the design and implementation of intelligent systems. |
|
An in depth understanding of the practical application of the fundamental principles of intelligent systems. |
|
An ability to analyse intelligent system problems and formulate appropriate solutions. |
Syllabus |
|
1 |
Week 1: Introduction to Intelligent systems:
The history of intelligent systems and their importance in real life applications, the characteristics of intelligent systems that serve to segregate them from other systems.
Week 2: Evolutionary Computation Algorithms:
Evolutionary computation algorithms as a sub-field of Artificial Intelligence with an emphasis on Genetic Algorithms (GAs), their structure and application.
Week 3: Rule-based Expert Systems:
How knowledge can be learnt, expressed and represented in the form of production rules, the characteristics of expert systems, forward and backward chaining inference techniques.
Week 4: Fuzzy Expert Systems:
The concept of fuzzy logic and its theoretical underpinning, fuzzy sets and rules, fuzzy inference techniques and the main steps in developing fuzzy expert systems.
Week 5: Artificial Neural Networks:
Artificial neural networks and perceptrons, the back propagation and feed forward neural network algorithms.
span>
Week 6: Deep Reinforcement Learning:
Deep neural networks and their applications, available deep learning tools for complex datasets.
Week 7: Hybrid Intelligent Systems:
Hybrid intelligent systems such as neuro-fuzzy systems, evolutionary neural networks and fuzzy evolutionary systems.
Week 8: Intelligent Systems Applications.
The application of intelligent systems in the context of: decision support, classification, decision trees, pattern recognition and data mining.
|
Teaching and Learning Strategies |
|
online Learning - Weekly seminar supported by asynchronous discussion in a virtual classroom environment facilitated by an online instructor. Number of hours per week that students are expected to attend the virtual classroom so as to participate in discussion, dedicated to group work and individual assessment is 7.5 |
Teaching Schedule |
Lectures | Seminars | Tutorials | Lab Practicals | Fieldwork Placement | Other | TOTAL | |
Study Hours |
60 Weekly seminar supported by asynchronous discussion in a virtual classroom environment facilitated by an online instructor. |
60 | |||||
Timetable (if known) |
Number of hours per week that students are expected to attend the virtual classroom so as to participate in discussion, dedicated to group work and individual assessment is 7.5
|
||||||
Private Study | 90 | ||||||
TOTAL HOURS | 150 |
Assessment |
||||||
EXAM | Duration | Timing (Semester) |
% of final mark |
Resit/resubmission opportunity |
Penalty for late submission |
Notes |
CONTINUOUS | Duration | Timing (Semester) |
% of final mark |
Resit/resubmission opportunity |
Penalty for late submission |
Notes |
Coursework | Weekly Discussion Qu | Whole session | 40 | No reassessment opportunity | Standard UoL penalty applies | Moot/debate: 8 discussion questions There is no reassessment opportunity, The nature of the adopted online learning paradigm is such that no reassessment opportunity is available, instead students failing the module will be offered the opportunity to retake the entire module. |
Coursework | One week: 20 minutes | Week 2 | 7 | No reassessment opportunity | Standard UoL penalty applies | Individual presentation: Comparison of intelligent and conventional systems There is no reassessment opportunity, The nature of the adopted online learning paradigm is such that no reassessment opportunity is available, instead students failing the module will be offered the opportunity to retake the entire module. |
Coursework | One week: 20 Minutes | Week 3 | 7 | No reassessment opportunity | Standard UoL penalty applies | Individual presentation: Expert systems There is no reassessment opportunity, The nature of the adopted online learning paradigm is such that no reassessment opportunity is available, instead students failing the module will be offered the opportunity to retake the entire module. |
Coursework | One Week: 750-1000 w | Week 4 | 10 | No reassessment opportunity | Standard UoL penalty applies | Case Study Analysis: Fuzzy Expert Systems There is no reassessment opportunity, The nature of the adopted online learning paradigm is such that no reassessment opportunity is available, instead students failing the module will be offered the opportunity to retake the entire module. |
Coursework | One Week: 750-1000 w | Week 5 | 10 | No reassessment opportunity | Standard UoL penalty applies | Case Study Analysis: Artificial Neural Networks There is no reassessment opportunity, The nature of the adopted online learning paradigm is such that no reassessment opportunity is available, instead students failing the module will be offered the opportunity to retake the entire module. |
Coursework | One Week: 750-1000 w | Week 6 | 10 | No reassessment opportunity | Standard UoL penalty applies | Case Study Analysis: Reinforcement Learning There is no reassessment opportunity, The nature of the adopted online learning paradigm is such that no reassessment opportunity is available, instead students failing the module will be offered the opportunity to retake the entire module. |
Coursework | Two weeks: 1500-2000 | Week 8 | 16 | No reassessment opportunity | Standard UoL penalty applies | Report: Group Work on Intelligent Systems Application There is no reassessment opportunity, The nature of the adopted online learning paradigm is such that no reassessment opportunity is available, instead students failing the module will be offered the opportunity to retake the entire module. Notes (applying to all assessments) (1) Due to nature of the online mode of instruction work is not marked anonymously. (2) Students who fail the module have the opportunity to repeat the entire module. (3) The "Standard UoL Penalty" for late submission that applies is the "Standard UoL Penalty" agreed with respect to online programmes offered in collaboration with Laureate Online Education. (4) For group work assessments groups typically comprise 3 to 4 students. Both group and individual contributions are assessed and integrated to produce a final mark for each student. |
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: The online programmes offered by the department of Computer Science in Collaboration with Laureate Online Education use online materials wherever possible including the online resources available within the University of Liverpool’s libraries. This module does not require a specific text book. |