UNIQUE SERIES AKTU Syllabus
BCS056BCS056H

Application of Soft Computing

L-T-P3-0-0 Credits3 Session2024-25 TypeTheory
Appears in 9 semesters · 9 branches

B.Tech Computer Science & Engineering · Sem 5 (Departmental Elective-II, code BCS056) · B.Tech Information Technology · Sem 5 (Departmental Elective-II, code BCS056) · B.Tech Artificial Intelligence & Machine Learning · Sem 5 (Departmental Elective-II, code BCS056) · B.Tech Artificial Intelligence & Data Science · Sem 5 (Departmental Elective-II, code BCS056) · B.Tech CSE (Artificial Intelligence) · Sem 5 (Departmental Elective-II, code BCS056) · B.Tech CSE (AI & ML) · Sem 5 (Departmental Elective-II, code BCS056) · B.Tech CSE (Data Science) · Sem 5 (Departmental Elective-II, code BCS056) · B.Tech Computer Science (Hindi) · Sem 5 (Departmental Elective-II, code BCS056H) · B.Tech Electrical & Computer Engineering · Sem 5 (Departmental Elective-II, code BCS056)

Download PDF

Syllabus

5 units · 40 lecture hours
Unit1

Unit 1: Neural Networks-I (Introduction & Architecture)

8 hrs

Neuron, Nerve structure and synapse, Artificial Neuron and its model, activation functions, Neural network architecture: single layer and multilayer feed forward networks, recurrent networks. Various learning techniques; perception and convergence rule, Auto-associative and hetro-associative memory.

Unit2

Unit 2: Neural Networks-II (Back propogation networks)

8 hrs

Architecture: perceptron model, solution, single layer artificial neural network, multilayer perception model; back propogation learning methods, effect of learning rule co-efficient ;back propagation algorithm, factors affecting backpropagation training, applications.

Unit3

Unit 3: Fuzzy Logic-I (Introduction)

8 hrs

Basic concepts of fuzzy logic, Fuzzy sets and Crisp sets, Fuzzy set theory and operations, Properties of fuzzy sets, Fuzzy and Crisp relations, Fuzzy to Crisp conversion.

Unit4

Unit 4: Fuzzy Logic –II (Fuzzy Membership, Rules)

8 hrs

Membership functions, interference in fuzzy logic, fuzzy if-then rules, Fuzzy implications and Fuzzy algorithms, Fuzzyfications & Defuzzificataions, Fuzzy Controller, Industrial applications

Unit5

Unit 5: Genetic Algorithm(GA)

8 hrs

Basic concepts, working principle, procedures of GA, flow chart of GA, Genetic representations, (encoding) Initialization and selection, Genetic operators, Mutation, Generational Cycle, applications.

Course Outcomes (COs)5 outcomes

After completion of the course student will be able to:

  1. CO1Recognize the feasibility of applying a soft computing methodology for a particular problemK2, K4
  2. CO2Know the concepts and techniques of soft computing and foster their abilities in designing and implementing soft computing based solutions for real-world and engineering problems.K4, K6
  3. CO3Apply neural networks to pattern classification and regression problems and compare solutions by various soft computing approaches for a given problem.K3, K5
  4. CO4Apply fuzzy logic and reasoning to handle uncertainty and solve engineering problemsK3, K4
  5. CO5Apply genetic algorithms to combinatorial optimization problemsK3

Note: The AKTU syllabus PDF of some branches prints this subject with small differences in the books (AI & ML, AI & Data Science, CSE (AI), CSE (AI & ML), CSE (Data Science)). Please also check the official AKTU PDF of your branch, linked at the end of your semester page.

Text books

  1. S. Rajsekaran & G.A. Vijayalakshmi Pai, “Neural Networks,Fuzzy Logic and Genetic Algorithm:Synthesis and Applications” Prentice Hall of India.
  2. N. P. Padhy,”Artificial Intelligence and Intelligent Systems” Oxford University Press. Reference Books:
  3. Siman Haykin,”Neural Networks” 3rd Edition Pearson Education
  4. Timothy J. Ross, “Fuzzy Logic with Engineering Applications” Wiley India.
  5. Kumar Satish, “Neural Networks” McGraw Hill

Official AKTU syllabus

This subject is on page 15 of the original AKTU PDF.

Official AKTU syllabus PDF ↗