Scribd
Upload
205 views

Semester Question Paper ECS607

This document contains questions from an examination on the topic of soft computing. It includes questions about [1] gradient descent functions, the differences between supervised and unsupervised learning, linguistic variables and predicate modifiers, antecedents and consequents, lambda cuts sets, structure learning vs parameter learning, and membership functions and neural network activation functions and biases. [2] Backpropagation network training algorithms and how they are better than other algorithms. [3] Performing max-min and max product composition on two given fuzzy relations. [4] Comparing medium wave and short wave receivers based on frequency range and plotting membership functions, and finding membership values for shapes using inference approaches. [5] Defining fuzzy arithmetic and different operations on

Uploaded by

Randeep Kumar sahu
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
205 views

Semester Question Paper ECS607

This document contains questions from an examination on the topic of soft computing. It includes questions about [1] gradient descent functions, the differences between supervised and unsupervised learning, linguistic variables and predicate modifiers, antecedents and consequents, lambda cuts sets, structure learning vs parameter learning, and membership functions and neural network activation functions and biases. [2] Backpropagation network training algorithms and how they are better than other algorithms. [3] Performing max-min and max product composition on two given fuzzy relations. [4] Comparing medium wave and short wave receivers based on frequency range and plotting membership functions, and finding membership values for shapes using inference approaches. [5] Defining fuzzy arithmetic and different operations on

Uploaded by

Randeep Kumar sahu
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 2

B.

Tech IBM VI (Sixth) Semester Examination 2018-19


Course Code: ECS607

Soft Computing
Time: 3 hours Max. Marks: 60

Note : Attempt all questions.

1. Answer any five question of the following (limit your answer to 50 words). ( 2x5=10)

a) Define gradient descent function?.

b) How supervised learning is differing from unsupervised learning?

c) .Define linguistic variable. What are predicate modifiers?

d) What are antecedents and consequents?

e) What is need of lamda cuts sets? How weak lamda cuts sets is differing from strong

lamda cuts sets?

f) How structure learning is differing from parameter learning?

g) What are membership functions, explain with suitable example.

h) What is need of activation function and bias in neural network?

2. Explain Back-Propagation Network (BPN) training algorithm. How BPN is better than other
training algorithms? (10)

Or

Design a hebb net to implement logical AND function (use bipolar inputs and targets). (10)

3. Two fuzzy are given by S=

Y1 y2 z1 z2 z3

x1 0.6 0.3 y1 1 0.5 0.3

R= x2 0.2 0.9 y2 0.8 0.4 0.7


. Obtain fuzzy relation T as a composition between the fuzzy relations.

(a) Max-min composition

(b) Max product composition (10)

Or

Explain the methods of membership value assignments with suitable example?

4. (a) Compare “ medium wave (MW)” and “short wave(SW)” receivers according to their
frequency range. Plot the membership functions using intuition. The linguistic variable are based on
the following: (10)

Medium wave receivers: frequency lesser than ≈ 106 Hz

Short wave receivers: frequency lesser than ≈ 106 Hz

(b)Using the inference approach, find the membership values for the triangular shapes I,R , E, IR
and T for a triangle with angle 45 degree, 55 degree and 80 degree. (10)

Or

Define defuzzification. Explain different types of methods for defuzzification. (10)

5. Define fuzzy arithmetic. Explain different operation of fuzzy number with suitable example.
(10)

Or

What are fuzzy quantifiers? Compare and contrast between absolute and relative quantifiers.
Also illustrate fuzzy controllers. (10)

6. (a) Discuss in details

 Probaility measure

 Fuzzy integrals

(b) Write short note on fuzzy ordering. (5+5=10)

Or

Explain role of fuzzy inference system. Compare and contrast between Mamdani and Takagi-
Sugeno fuzzy inference System. (10)

You might also like