Deep Learning Unit 3 Notes AKTU (BAI701)

Unit 3: Dimensionality Reduction – AKTU syllabus topics

• Linear Dimensionality Reduction (PCA, LDA)
• Autoencoders
• ConvNet Architectures (AlexNet, VGG, ResNet)
• Training a ConvNet (Weight Init, Hyperparameters)

Most asked AKTU PYQ questions from Unit 3

1. Q2c. Explain the role of manifold learning in dimensionality reduction. How does it compare to linear methods? (10 marks, 2024-25)
2. Q5a. Explain the concept of metric learning in the context of dimensionality reduction. How does it differ from traditional techniques like PCA (10 marks, 2024-25)
3. Q5b. Analyze the architectural differences between AlexNet, VGG, Inception, and ResNet. How do these architectures address the vanishing gradient problem? (10 marks, 2024-25)
4. Q2c. Describe the process of hyperparameter optimization in training a ConvNet. What are the key hyperparameters, and how do they influence network performance? (10 marks, 2024-25)
5. Q5a. Compare Principal Component Analysis and Linear Discriminant Analysis terms of their objectives and mathematical formulations. Provide examples of their use in classification tasks. (10 marks, 2024-25)
6. Q5b. Derive the reconstruction loss of an autoencoder. How does this loss relate to the dimensionality reduction capabilities of the network? (10 marks, 2024-25)
7. Q5a. Demonstrate the effect of Xavier and He initialization on training a ConvNet. (10 marks, 2024-25)
8. Q5b. Illustrate the role of residual connections in ResNet and their importance. (10 marks, 2024-25)
9. Q2c. What is the significance of the AlexNet architecture in deep learning history? (10 marks, 2024-25)
10. Q5b. Write short notes :- i) Deep Reinforcement ii) Autoencoder Architecture iii) VGG iv) SOA (10 marks, 2022-23)

Other Deep Learning units

• Unit 1 Notes
• Unit 2 Notes
• Unit 4 Notes
• Unit 5 Notes

Deep Learning previous year papers

• PYQ 2025-26
• PYQ 2024-25 (KCS078)
• PYQ 2024-25 (KOT076)
• PYQ 2022-23

Deep Learning exam preparation

• Deep Learning Unit 3 Important Questions
• Deep Learning Unit 3 PYQ
• Deep Learning Important Topics
• Deep Learning Predicted Paper