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

AKTU · BTECH · Semester 7 · Deep Learning · Session 2024-25 · PYQ

AKTU Deep Learning (KOT076) previous year question paper 2024-25 for B.Tech Semester 7. Covers Introduction to Neural Networks, Deep Networks…

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 2024-25

  1. Q1a. What is a loss function, and why is it essential for training a neural network? (2 marks, 2024-25)
  2. Q1b. What is stochastic gradient descent? (2 marks, 2024-25)
  3. Q1c. Explain the significance of the “AI Winter” in deep learning history. (2 marks, 2024-25)
  4. Q1d. What is the probabilistic theory of deep learning? (2 marks, 2024-25)
  5. Q1e. Define Linear Discriminant Analysis (LDA). (2 marks, 2024-25)
  6. Q1f. Explain how distance metrics are used in machine learning. (2 marks, 2024-25)
  7. Q1g. Define non-convex optimization. (2 marks, 2024-25)
  8. Q1h. What is generalization in deep learning? (2 marks, 2024-25)
  9. Q1i. What is WaveNet, and why is it significant for audio generation? (2 marks, 2024-25)
  10. Q1j. What is Word2Vec? (2 marks, 2024-25)
  11. Q2a. Illustrate how activation functions like ReLU and Sigmoid work in a shallow network. (10 marks, 2024-25)
  12. Q2b. Explain the role of the generator and discriminator in GANs. (10 marks, 2024-25)
  13. Q2c. What is the significance of the AlexNet architecture in deep learning history? (10 marks, 2024-25)
  14. Q2d. Explain the role of STNs in addressing spatial invariance in deep learning. (10 marks, 2024-25)
  15. Q2e. Describe the role of deep learning in bioinformatics applications. (10 marks, 2024-25)
  16. Q3a. Explain the purpose of backpropagation in training neural networks. (10 marks, 2024-25)
  17. Q3b. Describe the role of stochastic gradient descent (SGD) in optimization. (10 marks, 2024-25)
  18. Q4a. Demonstrate the working of a CNN on image classification tasks. (10 marks, 2024-25)
  19. Q4b. Demonstrate how batch normalization reduces internal covariate shift. (10 marks, 2024-25)
  20. Q5a. Demonstrate the effect of Xavier and He initialization on training a ConvNet. (10 marks, 2024-25)
  21. Q5b. Illustrate the role of residual connections in ResNet and their importance. (10 marks, 2024-25)
  22. Q6a. Explain how LSTMs address the vanishing gradient problem in RNNs. (10 marks, 2024-25)
  23. Q6b. Explain how RNNs are used for next-word prediction in text data. (10 marks, 2024-25)
  24. Q7a. Describe how attention mechanisms improve the performance of image captioning models. (10 marks, 2024-25)
  25. Q7b. Explain how semantic segmentation helps in scene understanding. (10 marks, 2024-25)

AKTU paper codes: BAI701, KCS078, KDS078, KOT076

Deep Learning previous year papers

More Deep Learning resources

Browse all notes · Semester 7 notes