Gujarat Technological UniversityWinter 2025 examination

GTU 3171613 Pattern Recognition Winter 2025 Question Paper & PDF

B.E. · IT Engineering · Semester 7 · Subject code 3171613
Download official PDFView PDF here
Share with your class
Total
70 marks
To pass
23 marks (33%)
Duration
2.5 Hours 10:30 AM – 1:00 PM
Questions
5 with internal choice
No solutions on this paper yetNeed them for your exam? Ask once. Papers that students ask for are solved first, and we aim to add them within 24 hours.

12 of 25 questions on this paper were also asked in other years. Each is marked below with the years it appeared.See all 18 repeated 3171613 questions, most asked first

Q.1

14 Marks
(a)
3 marksAsked in 2 of 3 papers

Define the following terms: conditional probability, joint probability and independent events.

Also asked in Summer 2026 Q1b

(b)
4 marks

Find inner product and outer product of following two vectors U and V, where U = [2 7 5 6] and V = [4 1 7 2]

(c)
7 marks
(
1)Suppose we are rolling a fair dice. The possible outcomes are 1, 2, 3, 4, 5 and 6. Let random variable X represent the outcomes. Calculate the expected value of X i.e E[X] ?
2)Suppose a bag has total 10 balls. Out of 10 balls, 6 are red, 3 are blue and 1 is green. Consider following events A and B. Calculate conditional probability P(A|B). Event A: Drawing a red ball from the bag. Event B: Drawing a ball that is not green.
3)Define : Autocorrelation

Q.2

14 Marks
(a)
3 marks

State for each problem, whether it belongs to supervised learning or unsupervised learning or none of the two ?

1Predict decease from blood sample
2Group audio files based on language of speakers
3Face Recognition to unlock mobile phone
4Predict sales of a product
5Group applicants for a job as per their nationality
6Learning to play chess
(b)
4 marksAsked in 2 of 3 papers

Consider two class classification problem. The classes are denoted as w1 and w2. Apply Baye’s minimum risk classification rule to decide whether sample x belongs to class w1 or w2. Use the following data: P(w1) = 0.6, P(w2) = 0.4, P(x) = 0.74, P(x|w1) = 0.75, P(x|w2) = 0.4. Loss parameters are: λ11 = 0.3, λ12 = 0.7, λ21 = 0.65, λ22 = 0.35.

Also asked in Summer 2025 Q2c

(c)
7 marksAsked in 2 of 3 papers

[1] Explain the two types of states in Hidden Markov Model. [2] Explain the two types of probabilities in Hidden Markov Model. [3] Explain step by step Hidden Markov Model Algorithm.

Also asked in Summer 2026 Q3c

(c)
7 marksAsked in 2 of 3 papers
Discus concept of Gaussian Mixture Model.

Also asked in Summer 2026 Q3c OR

Q.3

14 Marks
(a)
3 marks

Assume marks obtained by students in an examination follows normal distribution. The marks obtained are : 40, 45, 50, 30, 55, 70, 83, 90, 25, 66. Find parameters of normal distribution using Maximum Likelihood Estimation.

(b)
4 marksAsked in 2 of 3 papers
Explain with an example why large dimension of dataset is not desirable ?

Also asked in Summer 2025 Q3a

(c)
7 marks

Consider the below given two dimensional dataset with two features X1 and X2. Group the records into clusters using Single Linkage Hierarchical clustering and draw the dendogram. Use Euclidean distance. Sr. No. X1 X2 S1 4 3 S2 1 4 S3 2 1 S4 3 8 S5 6 9 S6 5

(a)
3 marksAsked in 2 of 3 papers
What do you mean by parameter estimation ? Explain Bayesian estimation.

Also asked in Summer 2026 Q3b

(b)
4 marks

Compare Principal Component Analysis and Fisher’s Linear Discriminant Analysis.

(c)
7 marks

Consider the following dataset of age and salaries of employees. Apply K-Means clustering algorithm to divide data into TWO clusters. Start with employee E1 as centroid of first cluster and E2 as centroid of the second cluster. Use Euclidean distance. Employee code Employee Age Salary E1 20 500 E2 40 1000 E3 30 800 E4 18 300 E5 28 1200 E6 25 1400 E7 35 1800

Q.4

14 Marks
(a)
3 marks
Discuss working of MP (McCullochh Pitts) neuron.
(b)
4 marks
Explain following two activation functions used in neural networks:
1)Sigmoid
2)Tanh
(c)
7 marks
Write and explain Perceptron learning algorithm.
(a)
3 marks
Discuss working of classical Perceptron.
(b)
4 marks

Explain following two activation functions used in neural networks:

1)RELU
2)Softmax
(c)
7 marksAsked in 2 of 3 papers
Explain gradient descent algorithm for learning neural network parameters.

Also asked in Summer 2026 Q5b OR

Q.5

14 Marks
(a)
3 marks
Discuss idea of convolution operation with an example.
(b)
4 marksAsked in 2 of 3 papers
Discuss various types of non-numeric/notional data.

Also asked in Summer 2026 Q5a OR

(c)
7 marksAsked in 3 of 3 papers
Explain working of SVM.

Also asked in Summer 2026 Q5b, Summer 2025 Q5a

(a)
3 marksAsked in 2 of 3 papers

Discuss idea of pooling operating used in Convolutional Neural Networks (CNNs) with an example.

Also asked in Summer 2025 Q5c

(b)
4 marksAsked in 2 of 3 papers
Explain working of Recurrent Neural Networks (RNN).

Also asked in Summer 2025 Q5b

(c)
7 marksAsked in 3 of 3 papers
Explain working of Classification and Regression Trees.

Also asked in Summer 2026 Q5c, Summer 2025 Q5c OR

More Pattern Recognition papers

Questions repeat across sessions. Working through two or three papers shows you which topics GTU asks most.

Summer 202670 marks · 5 questions
Summer 202570 marks · 5 questions

Other Semester 7 subjects

BE IT

2171607
Big Data Analytics
3171608
Wireless Communication
3171609
Software Project Management
3171610
Agile Development and UI/UX design

Preparing with friends?

Send this paper to your class group. Every question has its own link.

About this paper

Official Gujarat Technological University (GTU) examination paper for Pattern Recognition (Winter 2025, B.E. · IT Engineering, Sem 7). Features complete 70-mark regular & remedial examination pattern, official marking distribution across all 5 questions, and direct 1-click official PDF download.

Transcribed for student exam preparation from Gujarat Technological University official examination archives. Questions, syllabus guidelines, and curriculum marking schemes remain the intellectual property of Gujarat Technological University.

Download official PDF All Pattern Recognition Papers (3) →Report a typo or correction
ViewDownload PDF