Scribd
Upload
11 views

Soft Computing

Engeneering

Uploaded by

Augusto Klinton
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
11 views

Soft Computing

Engeneering

Uploaded by

Augusto Klinton
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 5

Q.2.

Answer ALL questions


a. Define a Fuzzy set and singleton pair.
b. Define α-cut and strong α-cut in fuzzy set.
c. What do you understand by threshold in ANN?
d. Explain two-point crossover in binary coded GA.
e. Define reversing process in mutation.
f. What is a linguistic variable?
g. Write different applications of soft computing
h. Define Euclidean distance.
i. State competitive learning rule.

PART – C: (Long Answer Questions)

Answer ALL questions


1. a. Two fuzzy sets are represented as:
0.2 0.5 1 0.7
𝐴= + + +
𝑥1 𝑥2 𝑥3 𝑥4

0.9 0.6 0.7 0.1


𝐵= + + +
𝑥1 𝑥2 𝑥3 𝑥4
Find (i) 𝐴 ∩ 𝐵𝑐
(ii) 𝐴⨁𝐵
(iii) 𝐴⨂𝐵
(iv) 𝐴 − 𝐵𝑐
b. State and proof De Morgan’s Laws for two fuzzy sets.
2. a. State and explain fuzzy membership functions.
b. Define Defuzzification and explain different defuzzification techniques
3. a. State and explain FIS with suitable diagram.
b. Differentiate between fuzzy logic and crisp logic with examples.
4. a. Two fuzzy sets are represented as:
0.5 0.1 0.3 0.6
𝐴= + + +
𝑥1 𝑥2 𝑥3 𝑥4

0.8 0.5 0.3 0.1


𝐵= + + +
𝑥1 𝑥2 𝑥3 𝑥4
Find (i) 𝐴 ∪ 𝐵
(ii) 𝐴 ∩ 𝐵
(iii) 𝐴 − 𝐵
(iv) 𝐴 − 𝐵𝑐
b. Differentiate between supervised and unsupervised learnings.
5.a. Briefly describe on fuzzy based rules.
b. Explain perceptron learning with algorithm.
6.a. How ANN is like biological neural network? Explain.
b. Explain tournament selection in GA with example.

Page 1 of 5
PART – B: (Short Answer Questions)

Q.2. Answer ALL questions


a. If a fuzzy set is represented as:
0.3 0.7 0.9
𝐴= + +
𝑥1 𝑥2 𝑥3
Find CONC(A) and DIL(A)
b. Define fuzzy Singleton pair.
c. A fuzzy set is given by:
𝐴 = {(𝑥1,0.2), (𝑥2,0.8),(𝑥3, 0.5), Find
Ac
d. Define involution operation in Fuzzy set.
e. Define commutativity and associativity properties for fuzzy sets.
f. Define concentration and dilation of a fuzzy set.
g. How are composition of relations found?
h. Enumerate different fuzzy membership functions.
i. List different defuzzification methods.
j. Define centroid method for defuzzification.

PART – C: (Long Answer Questions)

Answer ALL questions


1. a. Two Fuzzy relations are represented as:
0.1 0.3 0.4 0.5 0.2
𝑅1 = 𝑎𝑛𝑑 𝑅2 =0.7 0.1
0.2 0.1 0.5 0.2 0.6
Find following compositions:
(i) 𝑅1 𝑜 𝑅2
(ii) 𝑅1 ⨂̇ 𝑅2
b. Briefly explain on Mamdani and Sugeno controllers.

2. a. Two fuzzy sets are given by:


𝐴 = {(𝑥1,0.2), (𝑥2,0.8), (𝑥3, 0.5)}
𝐵 = {(𝑥1,0.6),(𝑥2, 0.2), (𝑥3,0.9)}
Find
(i) 𝐴𝐶 ∪ 𝐵𝐶
(ii) 𝐴 ∩ 𝐵𝐶
(iii) 𝐴 − 𝐵𝐶
(iv) 𝐴𝐶 − 𝐵𝑐
b. Two fuzzy sets are given by:
𝐴 = {(𝑥1,0.1), (𝑥2,0.6), (𝑥3, 0.5)}
𝐵 = {(𝑥1,0.8),(𝑥2, 0.2), (𝑥3,0.4)}
State and Prove De Morgan’s Laws
3. a. Differentiate between fuzzy Logic and crisp Logic.

b. Explain different operations on fuzzy sets.

Page 2 of 5
4. a. Explain fuzzy cross product between two fuzzy sets.

b. Explain different properties of fuzzy sets.

b. Two Fuzzy relations are represented as:


0.1 0.5 0.7 0.8 0.1 0.6
𝑅1 = 0.3 0.9 0 𝑎𝑛𝑑 𝑅2 = 0.7 0.9 0.8
1 0.5 0.6 0 0 1
Find
(i) 𝑅1 ∩ 𝑅2
(ii) 𝑅1 ∪ 𝑅2
6.a. Explain different operations of Fuzzy relations

PART – B: (Short Answer Questions) (2 Marks)

Q.2. Answer ALL questions


a. Define dendrites and synapse in biological neurons.
b. Explain on threshold in a neural network.
c. State activation function in neural network.
d. Draw the architecture of different ANNs.
f. Define unipolar and bipolar sigmoid activation functions.
g. How is threshold decided in MP neuron?
h. Explain perceptron learning rule.
i. Explain different phases of back propagation algorithm.
j. Define radial basis function with suitable equation.

PART – C: (Long Answer Questions)

Answer ALL questions


1. a. Design an Ex-OR gate using MP neuron.
b. Explain RBF neural network with algorithm.
2. a. State and explain back propagation algorithm with proper architecture.
3. a. Design an OR gate using Mc-Culloch neural network.
b. Construct a KSOFM to cluster four given vectors [0 0 1 1], [1 0 0 0], [0 1 1 0], and
[0 0 0 1] with initial learning rate of 0.5 and to produce two clusters.
4. a. Using back propagation algorithm train the following network with a target of 1
and learning rate 0.5 for unipolar sigmoid activation function and with inputs x1
= 1, and x2=1.

Page 3 of 5
b. Design a bipolar AND gate using perceptron neural network.
5.a. Explain Competitive learning with suitable algorithm.
b. Design an OR gate using Perceptron network neural network.

PART – B: (Short Answer Questions)

Q.2. Answer ALL questions


a. Define Genetic algorithm.
b. Explain optimization problems in Engineering.
c. Give few drawbacks in traditional optimization approach.
d. Define Genotypes and Phenotypes.
e. State order encoding.
f. Explain rank-based selection in GA
g. Define two-point crossover with example.
h. Define multipoint crossover with example.
i. How uniform crossover is different than shuffle crossover?
j. State the advantages of ANFIS system.

PART – C: (Long Answer Questions) (15 Marks)

Answer ALL questions


1. a. Draw the flow chart for Genetic Algorithm and List out different GA operators.
b. State and explain binary coded crossover techniques.
2. a. Two Parent chromosomes are represented as:
1 1 1 0 1 1 1 0 1 1

0 1 1 1 0 1 0 0 1 0
The chromosomes use multi-point crossover scheme with crossover points as
1,4,6. Find the children chromosomes.
b. Explain different mutation processes for binary coded GA with suitable example.
3. a. Maximize 𝑓(𝑥)=𝑥2
Subjected to : 0 < x < 15 using GA.
b. Explain ANFIS network with suitable diagram.
4. a. Explain different convergence criteria in Genetic Algorithm
b. State and explain single point, two point, and multi-point crossover techniques in
binary coded GA.
5.a. Two Parent chromosomes are represented as:
1 0 1 0 0 1 1 0 0 1

1 1 1 1 0 1 0 0 1 0
The chromosomes use multi-point crossover scheme with crossover points as
2,5,7. Find the children chromosomes.

Page 4 of 5
b. Minimize 𝑓(𝑥)=𝑥
Subjected to : 0 < x < 8 using GA.
6.a. Explain different techniques used in real valued crossover in GA
b. Explain different encoding schemes used in GA.

--- End of Paper ---

Page 5 of 5

You might also like