Machine Learning RGPV Notes in Hindi

Computer Science Engineering Tutorials in Hindi 6th Semester Notes in Hindi Year: 2026

Set A

Engineering Student Sample Exam Paper 2026 (RGPV)

New Scheme Based On AICTE Flexible Curricula

Bachelor of Technology (B.Tech.) VI Semester

CSIT-602 (DC) – MACHINE LEARNING

MODEL QUESTION PAPER – SET A

Time : Three Hours
Maximum Marks : 70

Note :

i) Attempt any five questions.

ii) All questions carry equal marks.

iii) In case of any doubt or dispute, the English version shall be treated as final.

i) किन्हीं पाँच प्रश्नों को हल कीजिए।

ii) सभी प्रश्नों के समान अंक हैं।

iii) किसी भी प्रकार के संदेह अथवा विवाद की स्थिति में अंग्रेजी भाषा को अंतिम माना जायेगा।

Q.1

a) Define Machine Learning. Explain its scope, limitations and major applications.
मशीन लर्निंग को परिभाषित कीजिए। इसके क्षेत्र, सीमाएँ तथा प्रमुख अनुप्रयोगों की व्याख्या कीजिए।

b) Explain supervised learning and unsupervised learning with suitable examples.
उपयुक्त उदाहरण सहित सुपरवाइज्ड तथा अनसुपरवाइज्ड लर्निंग समझाइए।

Q.2

a) Explain Linear Regression with hypothesis function and cost function.
हाइपोथेसिस फंक्शन तथा कॉस्ट फंक्शन सहित Linear Regression समझाइए।

b) Describe the importance of data preprocessing in Machine Learning. Explain normalization and feature scaling.
मशीन लर्निंग में डेटा प्री-प्रोसेसिंग का महत्व बताइए। नॉर्मलाइजेशन तथा फीचर स्केलिंग समझाइए।

Q.3

a) Explain Gradient Descent algorithm and its variants used for optimization.
ऑप्टिमाइजेशन हेतु प्रयुक्त ग्रेडिएंट डिसेंट एल्गोरिथ्म तथा उसके प्रकार समझाइए।

b) Differentiate between Sigmoid, ReLU and Tanh activation functions.
Sigmoid, ReLU तथा Tanh एक्टिवेशन फंक्शनों में अंतर लिखिए।

Q.4

a) Explain the architecture of Convolutional Neural Network (CNN) with neat diagram.
सुस्पष्ट आरेख सहित Convolutional Neural Network (CNN) की संरचना समझाइए।

b) Explain convolution, padding, stride and pooling operations used in CNN.
CNN में प्रयुक्त Convolution, Padding, Stride तथा Pooling क्रियाओं की व्याख्या कीजिए।

Q.5

a) What is Autoencoder? Explain its architecture and applications.
ऑटोएन्कोडर क्या है? इसकी संरचना तथा अनुप्रयोगों की व्याख्या कीजिए।

b) Explain Transfer Learning and One-Shot Learning with suitable examples.
उपयुक्त उदाहरण सहित Transfer Learning तथा One-Shot Learning समझाइए।

Q.6

a) Define Reinforcement Learning. Explain Agent, Environment, Reward and Policy.
रीइन्फोर्समेंट लर्निंग को परिभाषित कीजिए। Agent, Environment, Reward तथा Policy समझाइए।

b) Explain Markov Decision Process (MDP) and Bellman Equation.
मार्कोव निर्णय प्रक्रिया (MDP) तथा बेलमैन समीकरण समझाइए।

Q.7

a) Explain Support Vector Machine (SVM) and the concept of support vectors.
Support Vector Machine (SVM) तथा Support Vectors की अवधारणा समझाइए।

b) Describe Bayesian Learning and Bayes Theorem with suitable example.
उपयुक्त उदाहरण सहित Bayesian Learning तथा Bayes प्रमेय की व्याख्या कीजिए।

Q.8

Write short notes on any two:
किन्हीं दो पर संक्षिप्त टिप्पणी लिखिए :

  1. Natural Language Processing (NLP) / प्राकृतिक भाषा प्रसंस्करण
  2. Batch Normalization / बैच नॉर्मलाइजेशन
  3. Computer Vision Applications / कंप्यूटर विज़न के अनुप्रयोग
  4. TensorFlow and Keras Framework / TensorFlow एवं Keras फ्रेमवर्क
**********
💡
Exam Tip

Practice time management while solving these papers

Study Smart

Focus on frequently asked questions and important topics

📚
Practice All Sets

Solve all three sets to cover maximum question patterns

Machine Learning RGPV Notes in Hindi Question Papers - Computer Science Engineering Tutorials in Hindi

Download Machine Learning RGPV Notes in Hindi previous year question papers for Computer Science Engineering Tutorials in Hindi 6th Semester Notes in Hindi. These RGPV question papers help you understand the exam pattern, important topics, and question distribution.

How to Use These Question Papers Effectively

  • Solve papers in exam-like conditions with time limits
  • Identify your weak areas and focus on them
  • Compare your answers with standard solutions
  • Practice all three sets (Set A, Set B, Set C) to cover different question patterns
  • Revise important concepts before attempting papers