COMPUTATIONAL INTELLIGENCE - 2020/1
Module code: COM3013
In light of the Covid-19 pandemic the University has revised its courses to incorporate the ‘Hybrid Learning Experience’ in a departure from previous academic years and previously published information. The University has changed the delivery (and in some cases the content) of its programmes. Further information on the general principles of hybrid learning can be found at: Hybrid learning experience | University of Surrey.
We have updated key module information regarding the pattern of assessment and overall student workload to inform student module choices. We are currently working on bringing remaining published information up to date to reflect current practice in time for the start of the academic year 2021/22.
This means that some information within the programme and module catalogue will be subject to change. Current students are invited to contact their Programme Leader or Academic Hive with any questions relating to the information available.
This module gives an introductory yet up-to-date description of the fundamental technologies of computational Intelligence, including evolutionary computation, neural computing and their applications. Main streams of evolutionary algorithms and meta-heuristics, including genetic algorithms, evolution strategies, genetic programming, particle swarm optimization will be taught. Basic neural network models and learning algorithms will be introduced. Interactions between evolution and learning, real-world applications to optimization and robotics, and recent advances will also be discussed.
JIN Yaochu (Computer Sci)
Number of Credits: 15
ECTS Credits: 7.5
Framework: FHEQ Level 6
JACs code: I400
Module cap (Maximum number of students): N/A
Overall student workload
Independent Learning Hours: 106
Lecture Hours: 24
Laboratory Hours: 22
Prerequisites / Co-requisites
Good skill in C/C++ programming, good knowledge in mathematics (calculus)
Lesson 1: Introduction
- Natural intelligence
- Computational intelligence
- Understanding nature and solving engineering problems
- Professional organizations, major journals and conferences
Lesson 2: Evolutionary Algorithms
- A generic framework
- Genetic representations
- Genetic variations
- Selection schemes
Lesson 3: Swarm Intelligence
- Swarm intelligence in nature
- Particle swarm optimization
- Adaptive PSO
Lesson 4: Multi-Objective Evolutionary Algorithms
- Dynamic weighted aggregation
- Dominance-based selection
- Elitist non-dominated sorting genetic algorithms
- Performance measures
Lesson 5: Neural Network Models
- Multi-layer perceptrons
- Radial-basis-function networks
- Other neural network models
Lesson 6: Learning Algorithms
- Supervised learning
- Unsupervised learning
- Other learning schemes
Lesson 7: Hybrid Systems I
- Evolutionary optimization of neural networks
- Knowledge extraction from neural networks
- Knowledge incorporation into neural networks
Lesson 8: Hybrid Systems II
- Memetic algorithms
- Baldwin learning
- Lamarckian learning
- Meta-memetic algorithms
Lesson 9: Surrogate-Assisted Evolutionary Optimization
- Evolutionary computation for expensive problems
- Basic model management
- Advanced model management
- Evolutionary optimization of aerodynamic structures
Lesson 10: Evolutionary Optimization in Uncertain Environments
- Changing environments
- Search for robust solutions
- Tracking moving optima
Lesson 11: Evolutionary Developmental Systems
Gene regulatory networks
|Assessment type||Unit of assessment||Weighting|
|Coursework||COURSEWORK: INDIVIDUAL (PROGRAMMING)||50|
|Examination||FINAL PRACTICAL EXAM (2 HOURS)||50|
The assessment strategy is designed to provide students with the opportunity to demonstrate not only their ability to learn new knowledge, but also the ability to reuse the learned knowledge. This will be done in a step by step approach by training students for solving small, simple problems in terms of assignments, and then two pieces of major coursework that require programming skills and ability to solve new problems.
Thus, the summative assessment for this module consists of:
· A number of assignments will be given to the students for practice in each lecture. Minor programming tasks for using a c/c++ library will also be assigned to students for the lab session.
· Two coursework will be released to students at least 4 weeks before the submission deadline. The duration of final exam is 2 hours. The feedback on the coursework will be given to the students within two weeks after the submission deadline.
Formative assessment and feedback
· For assignments, reference solutions will be given to the students
· For coursework, feedback in terms of comments will be given to the students within 2 week time.
· A discussion of the issues will be given for each coursework.
- The module aims to demonstrate how computing techniques can be used to understanding natural intelligence, such as evolution, learning and development. Meanwhile, the module intends to show how knowledge gained from understanding natural intelligence be effectively used for solving engineering problems. Finally, this module should arouse students' interest in researching into nature-inspired computing techniques for understanding nature and problem solving. This module also aims to train the students for doing independent research, such as doing literature search, making a research proposal and presenting research results.
|1||Understand the main principles of computational intelligence||C|
|2||Gain hands-on knowledge and experience on designing evolutionary algorithms and neural network based learning algorithms for problem solving||K|
|3||Perform in-depth research on topics related to computational intelligence||PT|
C - Cognitive/analytical
K - Subject knowledge
T - Transferable skills
P - Professional/Practical skills
Methods of Teaching / Learning
The learning and teaching strategy is designed to train students the ability to independently learn knowledge and solve problems by reusing learning knowledge. The module involves many real-world problems from industry on optimisation and prediction.
The learning and teaching methods include:
The delivery pattern will consist of:
2-hour lectures (week 1-11)
2-hour lab, including coursework and assignments (week 2-11)
2-hour review (week 12)
Indicated Lecture Hours (which may also include seminars, tutorials, workshops and other contact time) are approximate and may include in-class tests where one or more of these are an assessment on the module. In-class tests are scheduled/organised separately to taught content and will be published on to student personal timetables, where they apply to taken modules, as soon as they are finalised by central administration. This will usually be after the initial publication of the teaching timetable for the relevant semester.
Upon accessing the reading list, please search for the module using the module code: COM3013
Programmes this module appears in
|Data Science MSc||1||Optional||A weighted aggregate mark of 50% is required to pass the module|
|Computer Science BSc (Hons)||1||Optional||A weighted aggregate mark of 40% is required to pass the module|
|Computing and Information Technology BSc (Hons)||1||Optional||A weighted aggregate mark of 40% is required to pass the module|
|Mathematics and Computer Science BSc (Hons)||1||Optional||A weighted aggregate mark of 40% is required to pass the module|
|Computer and Internet Engineering BEng (Hons)||1||Optional||A weighted aggregate mark of 40% is required to pass the module|
Please note that the information detailed within this record is accurate at the time of publishing and may be subject to change. This record contains information for the most up to date version of the programme / module for the 2020/1 academic year.