RS32348 – Artificial Neural Networks

RS32348 – Artificial Neural Networks

Course Outline

Course

:  RS 32348 –  Artificial Neural Networks

Core/Specialization

:  Specialization in Remote Sensing

Programme

:  Bachelor of Science Honors in Surveying Sciences

Department

:  RSGIS

Faculty

:  Faculty of Geomatics

Contact Hours

:  150

Year

:  III

Semester

:  II

Lecturer

:  

Room No.

:  

Telephone No.

:  

E-mail

: 

 

Synopsis

This course introduces students to students to neural networks and fuzzy theory from an engineering perspective. In the identification and control of dynamic systems, neural networks and fuzzy systems can be implemented as model free estimators and/or controllers

 

Contents

Neural Networks characteristics and History of development in neural networks principles, ANN terminology comparison with Biological Nervous System, Model of a neuron, Basic learning rules and theories, Feed Forward NN using Supervised Learning, Self – Organizing Neural Networks & Learning Vector Quantization Networks using Unsupervised learning, Recurrent Neural Networks, ANN Applications

 

Learning Outcomes

By the end of the course, students should be able to:

No.

Course Learning Outcome

Programme Outcome

Assessment Methods

1.

Describe  Neural Networks characteristics and History of development in neural networks principles

P01

Assignment / Final Exam

2.

Describe  ANN terminology comparison with Biological Nervous System

 

P01

Assignment / Final Exam

3.

Describe & design Feed Forward NN using Supervised Learning

P01, P02 & P05

Assignment / Final Exam

4.

Explain & design Self – Organising Neural Networks using Unsupervised learning

P01, P02 & P05

Assignment / Final Exam

5.

Define & design Recurrent Neural Networks  

P01, P02 & P05

Assignment / Final Exam

6.

Applications in ANN

P01, P02 & P05

Assignment / Final Exam

 

Student Learning Time (SLT)

Teaching and Learning Activities

Student Learning Time (hours)

Direct Learning

Lectures and Student Centered Learning (SCL)

27

Lab Practical

30

Independent Learning
  1. Preparation - Student Centred Learning activities

31
  1. Lab Practical activities

15
  1. Self-Learning (Library & Internet)

25
  1. Revision

15

Assessment
  1. Assignments

03
  1. Practical Assignments

02
  1. Final Examination(Practical)

02

TOTAL (SLT)

150

 

Teaching Methodology

Lectures, and individual and group assignments

 

References

  • Kosko Bart, Neural Network and Fuzzy systems : A Dynamical Systems Approach to Machine Intelligence – 2000
  • Livingstone,David J., Artificial Neural Network : Methods and application – 2008
  • Ripley, B.D., Pattern Recognition and Neural Network – 2004
  • White, Jay A, Pricing options with futures style margining, a genetic adaptive neural network appraoch – 2000
  • Juan Ramon Rabunal, ‎Julian Dorado , Artificial Neural Networks in Real-life Application- 2006
  • Puyin Liu, ‎Hong-Xing Li, Fuzzy Neural Network Theory and Application– 2004
  • MATLAB, Neural Network Toolbox,User’s Guide, http://www.mathworks.com/help/pdf_doc/nnet/nnet_ug.pdf

 

Grading

Assignment (x3)

20%

Practical Assignment (x2)

30%

Final Examination

50%

Total

100%