49
Assessment Methods
Continuous Assessment: 50%
Final Examination: 50%
WID3002
NATURAL LANGUAGE PROCESSING
Credit:
3
Course Pre-requisite(s):
None
Medium of Instruction:
English
Learning Outcomes
1. Identify the levels of natural language
processing.
2. Describe the natural language processing
techniques.
3. Apply basic algorithms of natural language
processing.
Synopsis of Course Content
The course introduces the theory and methods of
Natural Language Processing (NLP). It covers a
broad range of topics in NLP including basic text
processing, minimum edit distance, syntactic
analysis, and semantic analysis. In addition, it also
discusses some NLP applications such as machine
translation and automatic summarization.
Assessment Methods
Continuous Assessment: 50%
Final Examination: 50%
WID3003
NEURAL COMPUTING
Credit:
3
Course Pre-requisite(s):
None
Medium of Instruction:
English
Learning Outcomes
1. Describe the components of neuron and the
Artificial Neural Network (ANN) architecture.
2. Use appropriate data as input for the neural
network system.
3. Apply suitable learning rules for a given ANN
problem.
Synopsis of Course Content
This course covers topics such as the history,
design, biology motivation, and characteristics of
Artificial Neural Network to Deep Learning. It also
covers topics such as linear algebra, categorisation
of neural networks, learning rules of perceptron,
Hebbian
, backpropagation, and competitive
learning.
Assessment Methods
Continuous Assessment: 50%
Final Examination: 50%
WID3004
NUMERICAL METHODS
Credit:
3
Course Pre-requisite(s):
None
Medium of Instruction:
English
Learning Outcomes
1. Write equations using numerical methods.
2. Use numerical methods to solve differentiation
and integration problems.
3. Apply numerical methods to write computer
programs.
Synopsis of Course Contents
This course covers numerical analysis and the
computer implementation of numerical problems.
Topics include interpolation and function
approximation, system of linear equations, solving
algebraic equations, numerical differentiation and
integration, numerical solution of ordinary and
partial
differential
equations,
mathematical
modelling and computer simulation applications of
numerical method in various fields: computer
graphics, robotic, neural network, machine learning,
networking.
Assessment Methods
Continuous Assesssment: 50%
Final Examination: 50%
WID3005
INTELLIGENT ROBOTICS
Credit:
3
Course Pre-requisite(s):
None
Medium of Instruction:
English
Learning Outcomes
1. Describe various components of a robot and its
sensors.
2. Apply robot vision and speech processing
techniques in artificial intelligence problems.
3. Simulate robot.
Synopsis of Course Content
This course covers the fundamentals of robot
intelligence. It covers topics on the background of
robotic, applications (such as military, industries,
medical, and, search and rescue), effects of robots
on life, robot components, types of robots with
functions and applications, senses – vision (image,
pattern recognition, pixel analysis), acoustic,
speech, touch, olfactory (artificial nose), robot
kinematics, artificial emotions, navigation and
cognitive mapping, sensors and robot problem
solving. It also covers new development in robotics
(such as bio-inspired robotics, evolutionary robotic
and evolutionary algorithms).
