Deep Learning PYQ 2025-26 AKTU Question Paper

AKTU · BTECH · Semester 7 · Deep Learning · Session 2025-26 · PYQ

AKTU Deep Learning previous year question paper 2025-26 for B.Tech Semester 7. Covers Introduction to Neural Networks, Deep Networks, Dimensionality…

Open the interactive reader to study this resource on AcademicArk.

Deep Learning AKTU syllabus

  1. Unit 1: Introduction to Neural Networks
  2. Unit 2: Deep Networks
  3. Unit 3: Dimensionality Reduction
  4. Unit 4: Optimization & Generalization
  5. Unit 5: Case Studies & Applications

Questions in Deep Learning AKTU PYQ 2025-26

  1. Q1a. Define model in machine learning. (2 marks, 2025-26)
  2. Q1b. What is the difference between linear regression and logistic regression? (2 marks, 2025-26)
  3. Q1c. Discuss convolutional neural network (CNN)? (2 marks, 2025-26)
  4. Q1d. Name any two activation functions used in deep networks. (2 marks, 2025-26)
  5. Q1e. Describe the role of regularization during optimization. (2 marks, 2025-26)
  6. Q1f. Discuss the generalization in machine learning. (2 marks, 2025-26)
  7. Q1g. Name two applications of Word2Vec. (2 marks, 2025-26)
  8. Q2a. Derive the mathematical expression for the output of a single hidden-layer neural network. Explain the role of activation functions. (7 marks, 2025-26)
  9. Q2b. Describe how probabilistic models help reduce overfitting. Explain with examples. (7 marks, 2025-26)
  10. Q2c. Compare PCA and LDA. Explain how LDA maximizes class separability using scatter matrices. (7 marks, 2025-26)
  11. Q2d. Explain the optimization problem in deep learning. Why are deep learning loss surfaces highly non-convex? Discuss with suitable diagrams. (7 marks, 2025-26)
  12. Q2e. Describe the ImageNet dataset in detail. Explain its scale, structure, challenges, and importance in the evolution of deep learning. (7 marks, 2025-26)
  13. Q3a. Explain the backpropagation algorithm in detail. Derive the weight update rule for a multilayer perceptron. (7 marks, 2025-26)
  14. Q3b. Discuss the significance of activation functions in the Universal Approximation Theorem. (7 marks, 2025-26)
  15. Q4a. Compare batch normalization with layer normalization and instance normalization. (7 marks, 2025-26)
  16. Q4b. Explain the concept of semi-supervised learning with examples. Compare it with supervised and unsupervised learning. (7 marks, 2025-26)
  17. Q5a. Explain convolution operation mathematically, including stride, padding, and feature maps. (7 marks, 2025-26)
  18. Q5b. Compare AlexNet, VGG, Inception, and ResNet in terms of depth, performance, and computation. (7 marks, 2025-26)
  19. Q6a. Compare RNN, LSTM, and GRU networks. Highlight their advantages and use cases. (7 marks, 2025-26)
  20. Q6b. What is deep reinforcement learning? Explain its architecture involving policy networks, value networks, and environment interaction. (7 marks, 2025-26)
  21. Q7a. Explain how WaveNet differs from RNNs for sequential audio generation. (7 marks, 2025-26)
  22. Q7b. Explain the Word2Vec model. Discuss CBOW and Skip-Gram architectures with diagrams. (7 marks, 2025-26)

AKTU paper codes: BAI701, KCS078, KDS078, KOT076

Deep Learning previous year papers

More Deep Learning resources

Browse all notes · Semester 7 notes