Back close

Course Detail

Course Name Computational Intelligence
Course Code 24CLT676
Program M. Sc. Cognitive Sciences, Learning and Technology
Semester Soft Core
Credits 3
Campus Amritapuri

Syllabus

Unit I

Artificial Intelligence – a Brief Review – Pitfalls of Traditional AI – Need for Computational Intelligence Importance of Tolerance of Imprecision and Uncertainty – Overview of Artificial Neural Networks – Fuzzy Logic-Evolutionary Computation.

Unit II

Neural Networks: Biological and Artificial Neuron, Neural Networks, Supervised and Unsupervised Learning. Single Layer Perceptron – Multilayer Perceptron – Backpropagation Learning.

Unit III

Neural Networks as Associative Memories – Hopfield Networks, Bidirectional Associative Memory. Topologically Organized Neural Networks – Competitive Learning, Kohonen Maps.

Unit IV

Fuzzy Logic: Fuzzy Sets – Properties – Membership Functions – Fuzzy Operations. Fuzzy Logic and Fuzzy Inference – Applications. Evolutionary Computation – Constituent Algorithms.

Unit V

Swarm Intelligence Algorithms – Overview of other Bio-inspired Algorithms – Hybrid Approaches (Neural Networks, Fuzzy Logic, Genetic Algorithms etc.). Case Studies: Prediction Models, Optimization Models.

Course Objectives and Outcomes

Prerequisites:

  • Machine Learning
  • Programming languages
  • Probability

Course Objectives:

The Objective of the course is to make students familiar with basic principles of various computational methods of data processing that can commonly be called computational intelligence. This course introduces the fundamentals of key intelligent systems technologies including knowledge-based systems, neural networks, fuzzy systems, and evolutionary computation.

Course Outcomes:

COs Description
CO1 Understand the need for and importance of Computational intelligence.
CO2 Understand the concepts of neural networks and backpropagation learning.
CO3 Implement associative memory using neural networks.
CO4 Understand the idea of fuzzy logic in real-world problems.
CO5 Understand hybrid approaches to solve real-world problems.

CO-PO Mapping:

PO/PS O PO 1 PO2 PO 3 PO4 PO 5 PO6 PO7 PO8 PO9
CO
CO1 3
CO2 3 2 2
CO3 3 2 3
CO4 2 3 3
CO5 2 3 3

Evaluation Pattern:

Assessment Internal External
Active Participation in Class 10
*Continuous Assessment (CA) 40
Content produced over the course and submitted at

the last

50

*CA – Can be Quizzes, Assignment, Projects, and Reports, and Seminar

Textbooks / References

  • Laurene Fausett, Fundamentals of Neural Networks, 2nd edition, Pearson, 1993
  • Ross T J, ―Fuzzy Logic with Engineering Applicationsǁ, McGraw Hill, 1997.
  • Eiben A E and Smith J E, ―Introduction to Evolutionary Computingǁ, Second Edition, Springer,
    Natural Computing Series, 2007.
  • Kumar S, ―Neural Networks – A Classroom Approachǁ, Tata McGraw Hill, 2004.
  • Engelbrecht, A.P, ―Fundamentals of Computational Swarm Intelligenceǁ, John Wiley & Sons,
    2006.
  • Konar. A, ―Computational Intelligence: Principles, Techniques and Applicationsǁ, Springer
    Verlag, 2005.

DISCLAIMER: The appearance of external links on this web site does not constitute endorsement by the School of Biotechnology/Amrita Vishwa Vidyapeetham or the information, products or services contained therein. For other than authorized activities, the Amrita Vishwa Vidyapeetham does not exercise any editorial control over the information you may find at these locations. These links are provided consistent with the stated purpose of this web site.

Admissions Apply Now