B.TechSemester 72024-25Deep LearningKOT076

Deep Learning (KOT076) - AKTU Question Paper 2024-25

B.Tech · Semester 7 · Free PDF Download

This is the official AKTU Deep Learning Previous Year Question Paper for B.Tech Semester 7, academic session 2024-25. Published by Dr. A.P.J. Abdul Kalam Technical University (AKTU/UPTU), Lucknow. Free PDF download — no login required.

Course:B.Tech
Semester:Semester 7
Session:2024-25
University:AKTU / UPTU

Rate this paper

Questions Asked in 2024-25

Deep Learning (KOT076) — complete question paper · 100 marks · 3 Hours

Section AAttempt all questions in brief. 2 x 10 = 20
  • a
    What is a loss function, and why is it essential for training a neural network?
  • b
    What is stochastic gradient descent?
  • c
    Explain the significance of the “AI Winter” in deep learning history
  • d
    What is the probabilistic theory of deep learning?
  • e
    Define Linear Discriminant Analysis (LDA)
  • f
    Explain how distance metrics are used in machine learning
  • g
    Define non-convex optimization
  • h
    What is generalization in deep learning? 4 K1 i. What is WaveNet, and why is it significant for audio generation? 5 K1 j. What is Word2Vec?
Section BAttempt any three of the following: 10 x 3 = 30
  • a
    Illustrate how activation functions like ReLU and Sigmoid work in a shallow network
  • b
    Explain the role of the generator and discriminator in GANs
  • c
    What is the significance of the AlexNet architecture in deep learning history?
  • d
    Explain the role of STNs in addressing spatial invariance in deep learning
  • e
    Describe the role of deep learning in bioinformatics applications
Section CAttempt any one part of the following: 10 x 1 = 10
  • a
    Explain the purpose of backpropagation in training neural networks
  • b
    Describe the role of stochastic gradient descent (SGD) in optimization
  • a
    Demonstrate the working of a CNN on image classification tasks
  • b
    Demonstrate how batch normalization reduces internal covariate shift
  • a
    Demonstrate the effect of Xavier and He initialization on training a ConvNet
  • b
    Illustrate the role of residual connections in ResNet and their importance
  • a
    Explain how LSTMs address the vanishing gradient problem in RNNs
  • b
    Explain how RNNs are used for next-word prediction in text data
  • a
    Describe how attention mechanisms improve the performance of im age captioning models
  • b
    Explain how semantic segmentation helps in scene understanding

Question text is extracted from the official AKTU question paper PDF above. Hindi translations are omitted — every question is printed in English in the original paper. Last verified: 2026-08-23.

Deep Learning — Other Year Papers

AKTU Deep Learning PYQs from other sessions

Syllabus & More PYQs

Paper solve karne se pehle unit-wise syllabus dekh lo