| CODE | SCE4101 | ||||||||||||
| TITLE | Computational Intelligence 1 | ||||||||||||
| UM LEVEL | 04 - Years 4, 5 in Modular UG or PG Cert Course | ||||||||||||
| ECTS CREDITS | 5 | ||||||||||||
| DEPARTMENT | Systems and Control Engineering | ||||||||||||
| DESCRIPTION | This study-unit presents a set of nature-inspired computational methodologies developed to address complex real-world problems that are difficult and often impossible to solve using more traditional methods. The unit deals with artificial neural networks, fuzzy systems and evolutionary computation. More specifically the unit covers: 1. Introduction to Computational Intelligence: concept of intelligence, intelligence and computers, overview of the main generic methods for computational intelligence and their typical application domains. 2. Artificial Neural Networks: neuron models and their learning rules, types of neural networks and learning mechanisms, multilayer perceptron network, backpropagation algorithm, network design procedure, radial basis function networks, Hebbian learning rule and self-organizing maps. 3. Fuzzy Systems: fuzzy set theory, fuzzy logic, fuzzy systems for control and other applications. 4. Evolutionary Computation: genetic algorithms, particle swarm optimization, ant colony optimization. Study-unit Aims The aims of this study-unit are to introduce the main concepts and relevant algorithms for intelligent systems and to develop the ability to select and apply appropriate computational techniques. Learning Outcomes 1. Knowledge & Understanding: By the end of the study-unit the student will be able to: - recognize the need for computational intelligence (CI) to deal with complex real-world problems; - distinguish between the main CI methodologies (artificial neural networks, fuzzy systems and evolutionary computation); - describe the operation of a selected number of CI tools and the related algorithms such as: supervised and unsupervised learning schemes for both single neurons and multilayered neural networks, fuzzy control, the genetic algorithm, and particle swarm optimization. 2. Skills: By the end of the study-unit the student will be able to: - explain and/or derive a number of training algorithms for neural networks such as: the perceptron learning rule, the delta-rule, backpropagation for multilayered perceptrons, and training of self-organizing maps; - design and train a simple neural network; - work with fuzzy sets and apply fuzzy logic operations; - explain\demonstrate the main functions within a fuzzy system (fuzzification, inference and defuzzification); - design simple fuzzy systems; - list and explain the sequence of operations involved in a genetic algorithm; - list and explain the sequence of operations involved in particle swarm optimization. Main Text/s and any supplementary readings Main Text: 1) R. C. Eberhart, Y. Shi, Computational Intelligence: Concepts to Implementations, Morgan Kaufmann, 2007. Supplementary Text: 2) A. Engelbrecht, Computational Intelligence: An Introduction, Wiley&Sons, 2007. |
||||||||||||
| STUDY-UNIT TYPE | Lecture and Tutorial | ||||||||||||
| METHOD OF ASSESSMENT |
|
||||||||||||
| LECTURER/S | Nathaniel Barbara |
||||||||||||
|
The University makes every effort to ensure that the published Courses Plans, Programmes of Study and Study-Unit information are complete and up-to-date at the time of publication. The University reserves the right to make changes in case errors are detected after publication.
The availability of optional units may be subject to timetabling constraints. Units not attracting a sufficient number of registrations may be withdrawn without notice. It should be noted that all the information in the description above applies to study-units available during the academic year 2023/4. It may be subject to change in subsequent years. |
|||||||||||||