Scribd
Upload
31 views3 pages

MPhi Control Theory I Mid Term Paper 2022

The document describes a comprehensive exam for a PhD in Math. It contains 5 questions related to neural networks, fuzzy logic, and fuzzy sets. Question 1 involves solving a classification problem with a perceptron. Question 2 involves training an ADALINE network. Question 3 defines fuzzy set theory concepts. Question 4 involves operations on fuzzy sets like finding the disjunctive sum and max product of matrices. Question 5 involves a fuzzy bunch of functions.

Uploaded by

Amna Naqvi
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
31 views3 pages

MPhi Control Theory I Mid Term Paper 2022

The document describes a comprehensive exam for a PhD in Math. It contains 5 questions related to neural networks, fuzzy logic, and fuzzy sets. Question 1 involves solving a classification problem with a perceptron. Question 2 involves training an ADALINE network. Question 3 defines fuzzy set theory concepts. Question 4 involves operations on fuzzy sets like finding the disjunctive sum and max product of matrices. Question 5 involves a fuzzy bunch of functions.

Uploaded by

Amna Naqvi
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 3

CASPAM Bahauddin Zakariya University Multan

Examination: Comprehensive Examination 2023 PHD-Math


Course Title: Neural Network &fuzzy Engineering Course Code: Math-769
Teacher: Prof. Dr. Khalid Saifullah Syed Total Marks: 25

Questions Marks
Q.No.1 Solve the following classification problem with the perceptron rule. Apply each input
vector in order, for as many repetitions as it takes to ensure that the problem is solved. Draw a
graph of the problem only after you have found a solution

[] [ ] [ ] [ ]
{ p 1= 2 , t 1=0 }{ p 2= 1 , t 2=1} { p 3= −2 , t 3=0 } { p 4= −1 , t 4=1 }
2 −2 2 1
Where
w (0)=[0 0]b(0)=0 5
Q.No.2 (a) Suppose that we have the following input/target pairs:

[] [ ]
{ p 1= 1 ,t 1=1 } , { p 2= 1 , t 2=−1 }
1 −1
These patterns are used to train the ADALINE network with no bias. Train the network using LMS
algorithm, with the initial guess set to zero and a learning rate α =0.25 . Apply each reference
pattern only once during training. Draw the decision boundary at each stage.
3
(b) Show that multilayer network with linear transfer function is equivalent to a single-layer linear
network. 2

Q.No.3 Define the following with example of each:


(i) Fuzzy Set
(ii) α-Cut Set
(iii) Convex fuzzy set
(iv) Fuzzy Number
(v) Fuzzy Cardinality 5
Q.No.4(a) Find simple disjunctive sum of the following:
A=¿{(x1, 0.2),(x2, 0.7), (x3, 1), (x4, 0)}
B={(x1, 0.5),(x2, 0.3), (x3, 1), (x4,0.1)} 3+3
(b) For the following matrices A and B find sum and max product.

A= a b c
a 0.2 0.5 0.0
b 0.4 1.0 0.1
c 0.0 1.0 0.0
a b c
a 1.0 0.1 0.0
B=¿ b 0.0 0.0 0.5
c 0.0 1.0 0.1

QNo.5 There is fuzzy bunch of function X ={2 , 3 , 4 }


1

You might also like