Scribd
Upload
102 views2 pages

Calculation: Question 2: ANN-Multi Layer Perceptron (05 Marks)

This document contains information about an exam for an Artificial Intelligence program, including: - The date, time, and location of the midterm exam - Instructions for two questions on the exam about an artificial neural network and regression/correlation - Details of the questions, including tables of data and parameters for modeling tasks - A third question on genetic algorithms to optimize the dimensions of a box to minimize cost

Uploaded by

Hassan Sheikh
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
102 views2 pages

Calculation: Question 2: ANN-Multi Layer Perceptron (05 Marks)

This document contains information about an exam for an Artificial Intelligence program, including: - The date, time, and location of the midterm exam - Instructions for two questions on the exam about an artificial neural network and regression/correlation - Details of the questions, including tables of data and parameters for modeling tasks - A third question on genetic algorithms to optimize the dimensions of a box to minimize cost

Uploaded by

Hassan Sheikh
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/ 2

Name of the subject: Artificial Intelligence Program: BS (CS) Section: C

Faculty Name: Syed Sajjad Hussain Rizvi Marks allocated: 20 Duration 120 min
Date of Midterm Exam Monday April 05, 2021 11 AM to 1 PM
Note: Use of Calculator/ MS Excel/ Matlab or any other computing tool is allowed for
calculation

Question 2: ANN-Multi Layer Perceptron [05 Marks]


A Multi-Layer Perceptron (MLP) with one hidden layer, and back propagation learning method
is required to be designed to classify a two-dimensional data. You are given with the four
patterns (xi) along with their target classes (yi), Shown in Table 1. Following are the instructions
parameters given for training.
W11(hidden layer) -0.239
W12(hidden layer) 3
W21(hidden layer) -0.85
Initial weights
W22 (hidden layer) 4
W’11(output layer) -1
W’21(output layer) 4.45
Θ1(hidden layer) 1.253
Threshold Θ2(hidden layer) 1.464
Θ3(output layer) 0.77
Learning rate α 10
B1(hidden layer) -1
Bias Values B2(hidden layer) -1
B3(output layer) -1
Activation Function (hidden layer and output layer) Logsigmoid
Epoch 1
Your are required to compute following for ONLY ONE EPOCH
a. Updated weight of hidden and output layer
b. Updated threshold of hidden and output layer
c. Error in each output
d. Neural Schema
e. Output of each neuron in hidden and output layer
Table 1.
x1 x2 y
0 0 0
0 1 1
1 0 1
1 1 1

Page 1 of 2
Question 3: Regression & Correlation [05 Marks]
BENQ is a leading innovator of digital lifestyle devices dedicated to Bringing Enjoyment ‘N’
Quality to Life. P&G plan to purchase some new multimedia projector from BENQ for their
newly develop building an a IT manager you are requested to have a market survey about their
cost and expected life .A study was made by a research group to determine the relation between
price and life . The following data were recorded:

Price of Projector ($) (X) Life (Hrs) (Y)


40 385
20 400
25 395
20 365
30 475
50 440
Required
a. Determine and plot the regression equation
b. Compute the error coefficient
c. Estimate the projector life if the price is 300$
d. Compute correlation coefficient matrix

Question 4: Genetic Algorithm [05 Marks]


a. We want to construct a box whose base length is 3 times the base width. The material
used to build the top and bottom cost $10/ft2 and the material used to build the sides cost
$6/ft2. If the box must have a volume of 50ft3 determine the dimensions that will
minimize the cost to build the box.

b. Discuss the dimensions of Genetic Algorithm as the function of the following parameters

1. Generation
2. Cost/Fitness Function
3. Mutation
4. Chromosome
5. Geno and pheno types
6. Crossover
7. Selection methods

Page 2 of 2

You might also like