Scribd
Upload
7 views1 page

WWW - Manaresults.co - In: Neural Networks and Fuzzy Logic

This document is an examination question paper for a course on Neural Networks and Fuzzy Logic, intended for Electrical and Electronics Engineering students. It includes two parts: Part-A with short answer questions and Part-B with longer, detailed questions, covering topics such as reinforcement learning, neuron models, backpropagation, and fuzzy sets. The exam is scheduled for October/November 2020, with a total of 70 marks.

Uploaded by

NAYAK
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
7 views1 page

WWW - Manaresults.co - In: Neural Networks and Fuzzy Logic

This document is an examination question paper for a course on Neural Networks and Fuzzy Logic, intended for Electrical and Electronics Engineering students. It includes two parts: Part-A with short answer questions and Part-B with longer, detailed questions, covering topics such as reinforcement learning, neuron models, backpropagation, and fuzzy sets. The exam is scheduled for October/November 2020, with a total of 70 marks.

Uploaded by

NAYAK
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/ 1

Code No: R163202E R16 SET - 1

III B. Tech II Semester Regular/Supplementary Examinations, October/November - 2020


NEURAL NETWORKS AND FUZZY LOGIC
(Electrical and Electronics Engineering)
Time: 3 hours Max. Marks: 70
Note: 1. Question Paper consists of two parts (Part-A and Part-B)
2. Answer ALL the question in Part-A
3. Answer any FOUR Questions from Part-B
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
PART –A (14 Marks)
1. a) Justify your answer, “the information in the brain is adaptable whereas in the
computer it is strictly replaceable” [2M]
b) What is meant by Reinforcement learning? [2M]
c) Explain the limitations of the Hopfield network. [3M]
d) Define the following with examples (i) Power set (ii) Super set. [3M]
e) What do you mean by fuzzy inference? [2M]
f) Explain the concept of process identification. [2M]
PART –B (56 Marks)
2. a) Justify your answer “Humans beings are more intelligent than computers”. [7M]
b) Explain the following: (i) Spiking neuron model, (ii) Integrate and fire neuron [7M]
model.
3. a) What are the various types of neuron activation functions? Explain any two with a [7M]
neat sketch.
b) List out the differences between supervised and unsupervised learning with a neat [7M]
sketch.
4. a) What are the steps involved in the backpropagation algorithm? Explain. [7M]
b) What are learning difficulties in backpropagation and how do you overcome it? [7M]

5. a) How you can distinguish the crisp and fuzzy sets with examples? [7M]
b) Let us define two fuzzy sets [7M]
}
Find (i) (ii) Product of a fuzzy set with a crisp number
(iii) Power of a fuzzy set with (iv) Difference (v) .
6. a) Discuss the membership value assignment. [7M]
b) Compute by using the centroid method for the figure shown below. [7M]

7. What do you mean by fault diagnosis? Explain the fault diagnosis by using a [14M]
neural network with a neat sketch?
*****

|''|'''||''||'''|||| www.manaresults.co.in

You might also like