Â鶹´«Ã½

-


EE40098: Computational intelligence

Academic Year: 2018/9
Owning Department/School: Department of Electronic & Electrical Engineering
Credits: 6      [equivalent to 12 CATS credits]
Notional Study Hours: 120
Level: Masters UG & PG (FHEQ level 7)
Period:
Semester 1
Assessment Summary: CW 25%, EX 75%
Assessment Detail:
  • Core based coursework (computer program) (CW 25%)
  • Examination (EX 75%)
Supplementary Assessment:
Like-for-like reassessment (where allowed by programme regulations)
Requisites:
Description: Aims:
To provide students with an understanding of some of the principles of Computational Intelligence.

Learning Outcomes:
After successfully completing this unit the student should be able to:
Understand, be able to explain and implement the following types of computational intelligence techniques:
* Optimization
* Control
* Machine Learning
* Classification
Understand and be able to explain the biological inspiration behind computational intelligence systems

Skills:
Application of the techniques introduced in the lectures to Computational Intelligence: taught, facilitated and tested.

Content:

* Optimization: simulated annealing, steepest descent, genetic algorithms, the schema Theorem, representation, populations, selection, crossover mutation , swarm optimization
* Control: Fuzzy Logic comparison with crisp logic. linguistic variables, degree of membership, fuzzy rules, defuzzification.
* Classification: Neural Networks, MCP neuron, geometric interpretation. XOR problem. 1, 2, and 3 layer feed-forward networks. perceptron training rule, sigmoid function, back-propagation, K-nearest neighbour, Principal Component Analysis, Convolutional Neural Networks Feed-back networks.
* Bio-inspired: Neurophysiology: biological neuron systems, neuron models for simulation, problem solving in nature, biomimetic computing, swarm Intelligence: emergent behaviour, predator-prey models, conways game of life
* Machine Learning: decision tree learning, rule based machine learning, deep learning, support vector machines, Bayesian networks, reinforcement learning.
Programme availability:

EE40098 is Compulsory on the following programmes:

Department of Electronic & Electrical Engineering
  • TEXX-AFM01 : MSc Mechatronics
  • UEEE-AFM13 : MEng(Hons) Computer Systems Engineering (Year 4)
  • UEEE-AKM13 : MEng(Hons) Computer Systems Engineering with Year long work placement (Year 5)

EE40098 is Optional on the following programmes:

Department of Computer Science
  • USCM-AFM01 : MComp(Hons) Computer Science (Year 4)
  • USCM-AAM02 : MComp(Hons) Computer Science with Study year abroad (Year 5)
  • USCM-AKM02 : MComp(Hons) Computer Science with Year long work placement (Year 5)
Department of Electronic & Electrical Engineering
  • UEEE-AFM05 : MEng(Hons) Electronic and Communication Engineering (Year 4)
  • UEEE-AFM01 : MEng(Hons) Electrical and Electronic Engineering (Year 4)
  • UEEE-AKM01 : MEng(Hons) Electrical and Electronic Engineering with Year long work placement (Year 5)
  • UEEE-AFM12 : MEng(Hons) Electrical Power Engineering (Year 4)
  • UEEE-AKM12 : MEng(Hons) Electrical Power Engineering with Year long work placement (Year 5)
  • UEEE-AKM05 : MEng(Hons) Electronic and Communication Engineering with Year long work placement (Year 5)
  • UEEE-AFM14 : MEng(Hons) Electronic Engineering with Space Science & Technology (Year 4)
  • UEEE-AKM14 : MEng(Hons) Electronic Engineering with Space Science & Technology with Year long work placement (Year 5)
  • UEXX-AFM02 : MEng(Hons) Integrated Mechanical and Electrical Engineering (Year 4)
  • UEXX-AKM02 : MEng(Hons) Integrated Mechanical and Electrical Engineering with Year long work placement (Year 5)
Department of Mathematical Sciences

Notes:

  • This unit catalogue is applicable for the 2018/19 academic year only. Students continuing their studies into 2019/20 and beyond should not assume that this unit will be available in future years in the format displayed here for 2018/19.
  • Programmes and units are subject to change in accordance with normal University procedures.
  • Availability of units will be subject to constraints such as staff availability, minimum and maximum group sizes, and timetabling factors as well as a student's ability to meet any pre-requisite rules.
  • Undergraduates: .
  • Postgraduates: .