1/8/25, 4:15 PM .
Syllabus-2024-2025
(SOET)(BTech-Artificial_Intelligence_and_Machine_Learning)
Title of the Course Soft Computing Techniques
Course Code CSE0630
Part A
L T P C
Year 3rd Semester 6th Credits
3 1 0 4
Course Type Embedded theory and lab
Course Category Discipline Core
to give students knowledge of soft computing
theories fundamentals, i.e. of fundamentals of non-
traditional technologies and approaches to solving
Pre-Requisite/s Co-Requisite/s
hard real-world problems, namely of fundamentals
of artificial neural networks, fuzzy sets and fuzzy
logic and genetic algorithms.
CO1- To remember various concept of soft computing.(BL1-Remember)
CO2- To understand the basic concept of artificial neural networks, fuzzy sets, fuzzy logic
and genetic algorithms(BL2-Understand)
Course Outcomes CO3- Implementation of various supervised and unsupervised learning algorithms and
& Bloom's Level optimization techniques.(BL3-Apply)
CO4- To Analyze various soft computing algorithms and techniques.(BL4-Analyze)
CO5- To evaluate the state of the art of artificial neural networks, fuzzy logic and genetic
algorithms.(BL5-Evaluate)
SDG1(No poverty)
Skill Development ✖ SDG2(Zero hunger)
Entrepreneurship ✖ SDG4(Quality education)
Employability ✖ SDG8(Decent work and economic
Course Elements Professional Ethics ✖ SDG (Goals) growth)
Gender ✖ SDG9(Industry Innovation and
Human Values ✖ Infrastructure)
SDG12(Responsible consuption and
Environment ✖ production)
https://prabandh.itmuniversity.ac.in/exam/syllabusreport/ 1/4
1/8/25, 4:15 PM .
Part B
Modules Contents Pedagogy Hours
(Neural Networks: Introduction and
Architecture) Basic concepts of neural
networks, neuron, nerve structure and
synapse, model of an artificial neuron,
neural network architecture: single layer and Lectures with whiteboard/PPT, Recorded
1 10
multilayer feed forward networks, recurrent video/interactive videos, programming labs
networks. Neural networks characteristics,
various learning techniques; perception and
convergence rule, neural network
applications.
(Neural Networks: Back Propagation
Networks) Introduction of back propagation
networks, architecture: perceptron model,
solution, single layer artificial neural
network, model for multilayer perceptron
Lectures with whiteboard/PPT, Recorded
2 model; back propagation learning methods, 10
video/interactive videos, programming labs
effect of learning rule co-efficient; back
propagation algorithm, factors affecting back
propagation training, applications, variations
of standard back propagation algorithm,
research directions.
(Fuzzy Logic: Introduction) Basic concepts
of fuzzy logic, utility and limitations of fuzzy
systems, fuzzy sets and membership,
chance versus fuzziness, fuzzy sets and
Lectures with whiteboard/PPT, Recorded
3 classical (crisp) sets, fuzzy set theory and 10
video/interactive videos, programming labs
operations, properties of fuzzy sets,
operations on classical sets, properties of
classical sets, mapping of classical sets to
functions.
(Fuzzy Logic: Fuzzy Membership and Rules)
Features of the membership function,
various forms, fuzzification, defuzzification to Lectures with whiteboard/PPT, Recorded
4 10
crisp sets, defuzzification to scalars, logic video/interactive videos, programming labs
and fuzzy systems, fuzzy controller,
industrial applications.
(Genetic Algorithm) Genetic Algorithm (GA):
basic concepts, working principals, encoding
fitness function, reproduction, genetic
modeling: inheritance operator, cross over, Lectures with whiteboard/PPT, Recorded
5 10
inversion and deletion, mutation operator, video/interactive videos, programming labs
bitwise operator, generational cycle,
convergence of GA, application and
advances in GA.
https://prabandh.itmuniversity.ac.in/exam/syllabusreport/ 2/4
1/8/25, 4:15 PM .
Part C
Indicative-ABCA/PBL/
Modules Title Experiments/Field work/ Bloom's Level Hours
Internships
1-2 Assignment Experiments BL2-Understand 8
3-4 Quiz Others BL2-Understand 2
Part D(Marks Distribution)
Theory
Total Minimum Passing External Min. External Internal Min. Internal
Marks Marks Evaluation Evaluation Evaluation Evaluation
100 40 40 12 60
Practical
Total Minimum Passing External Min. External Internal Min. Internal
Marks Marks Evaluation Evaluation Evaluation Evaluation
100 50 40 20 60
Part E
Rajsekaran, S., & Vijayalakshmi Pai, G. A. (2003). Neural Networks, Fuzzy Logic and
Books Genetic Algorithm: Synthesis and Applications. Prentice Hall of India.
Sivanandam, S. N. (2018). Principles of Soft Computing. Wiley India.
Articles
Kumar, S. (2012). Neural Networks. Tata McGraw-Hill.
References Books
Padhy, N. P. (2005). Artificial Intelligence and Intelligent Systems. Oxford University Press.
MOOC Courses
Videos
Part F
Project 1 No project available
Project 2 No project available
Project 3 No project available
Project 4 No project available
Project 5 No project available
https://prabandh.itmuniversity.ac.in/exam/syllabusreport/ 3/4
1/8/25, 4:15 PM .
Course Articulation Matrix
COs PO1 PO2 PO3 PO4 PO5 PO6 PO7 PO8 PO9 PO10 PO11 PO12 PSO1 PSO2 PSO3
CO1 - - - - 2 2 - - - 2 - - 1 2 3
CO2 3 1 1 2 2 2 - - - 2 - - 1 2 3
CO3 2 2 - - 1 - - - - - - - 3 2 3
CO4 2 2 - 2 1 - - - - - - - 3 2 3
CO5 1 2 - 2 1 - - - - - - - 3 2 3
CO6 - - - - - - - - - - - - - - -
https://prabandh.itmuniversity.ac.in/exam/syllabusreport/ 4/4
