Scribd
Upload
10 views1 page

UEI704

The document outlines an examination paper for a course on Soft Computing Techniques at Thapar Institute, detailing questions on back-propagation networks, soft computing concepts, neural network calculations, and learning rules in artificial neural networks (ANN). It includes specific tasks such as calculating outputs for given input patterns and explaining activation functions. The paper is structured with various questions aimed at assessing students' understanding of key concepts in soft computing and ANN.

Uploaded by

vivesod153
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
10 views1 page

UEI704

The document outlines an examination paper for a course on Soft Computing Techniques at Thapar Institute, detailing questions on back-propagation networks, soft computing concepts, neural network calculations, and learning rules in artificial neural networks (ANN). It includes specific tasks such as calculating outputs for given input patterns and explaining activation functions. The paper is structured with various questions aimed at assessing students' understanding of key concepts in soft computing and ANN.

Uploaded by

vivesod153
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

E lay

Roll Number: 0
Thapar Institute of Engineering and Technology, Patiala
Department of Electrical and Instrumentation Engineering
B.E., MST Course Code: UEI704
Course Name: Soft Computing Techniques
September 28th 2022 Wednesday, 05.30 PM
Time: 2 Hours, M. Marks: 50 Name of Faculty: Dr. Saurabh Bhardwaj
Note: Assume missing data, if any, suitably‘

Q.1 i. Briefly explain about the architecture and training algorithm of back-propagation
network. +
3
ii. What do you understand with the term Soft computing. Write down three differences .
between Hard and soft computing.
10
Q.2 i. The following diagram represents a feed-forward neural network with one hidden 5
layer: +
5
0 0 =
$ 2
10
---411
0
The following table lists all the weights in the network:
wt.; = —2 w35 = 1
wr = 3 w45 = —1
wi I = 4 w36 = —1
W2 1 = -1 W46 = 1

Each of the nodes 3, 4, 5 and 6 uses t he following activation function:


00 21 1 if v ?.... 0
0 otherwise
where v denotes the weighted sum of a node. Each of the input nodes (1 :and 2) can only
receive binary values (either 0 or 1). Calculate the output of the network (v 5 and y 6)
.
for each of the input patterns:
Pattern: P1 P2 P3 P4
Node 1: 0 1 0 1
Node 2: 0 0 1 1

ii. Define sigmoid activation function and explain how this function exhibits a graceful
balance between
• linear and nonlinear behavior.

Q.3 i. What are the different types of learning rules in ANN? Discuss Hebbian learning with 7
proper mathematical formulation. +
3
ii. Why is it impossible for a single binary perceptron to solve the XOR problem?
=
10
Q.5 What is a perceptron? Write down the unified learning rule of single layer perceptron? 10
Prove that the rule will always convergip to weights that achieve the desired
classification.

You might also like