Page 111 - PG-Handbook23-24-finale

Synopsis of Course Content

This course introduces the core artificial intelligence concepts and skills that allow machines to mimic
human intelligence. It contains a theory component about the concepts and principles that underlie
modern AI algorithms, and a practice component to relate theoretical principles with practical
implementation. Coverage includes knowledge representation, logic, inference, problem solving, search
algorithms, game theory, perception, learning, planning, and agent design

Evaluation and Weightage
Continuous Assessment : 60%
Final Examination : 40%

WQF7006 Computer Vision and Image Processing

Learning Outcomes
At the end of this course, the students are able to:

1. Evaluate suitable image processing techniques to solve artificial intelligence problems.
2. Evaluate performances of image processing methods for a given artificial intelligence scenario.
3. Design and develop image processing systems in the artificial intelligence domain
Synopsis of Course Content

This course explores image processing techniques in solving artificial intelligence problems. Image
formation and image models are initial steps involved, It covers pixel and object level operations
including histogram, edge, and segment. Image enhancement and restoration are compared. Image
registration and image transform operations are included. Finally, image features and recognition
processes are given. Deep learning approach for computer vision is included

Evaluation and Weightage
Continuous Assessment : 60%
Final Examination : 40%

WQF7007 Natural Language Processing

Learning Outcomes
At the end of the course, students are able to:
1. Apply the Natural Language Processing (NLP) techniques in various domains.
2. Design a Natural Language Processing (NLP) solution to resolve issues related to unstructured
text.
3. Develop an NLP application by integrating all processes in the NLP pipeline which are pre-
processing, low level task and high level task.

Synopsis of Course Content
Natural language processing (NLP) is one of the most important areas in Artificial Intelligence (AI). This
course covers the theory and practice of NLP through techniques for different levels which are pre-
processing, low-level and high level. It also covers recent techniques and applications in NLP including
Sentiment Analysis, Machine Translation, Topic Modeling and Named Entity Recognition.

Evaluation and Weightage
Continuous Assessment : 70%
Final Examination : 30%