Deep Learning Unit 2 Notes AKTU (BAI701)

Unit 2: Deep Networks – AKTU syllabus topics

• History & Theory of Deep Learning
• Regularization & Batch Normalization
• Convolutional Networks
• Generative Adversarial Networks (GAN)
• Semi-supervised Learning

Most asked AKTU PYQ questions from Unit 2

1. Q4b. How does semi-supervised learning differ from supervised and unsupervised learning? Discuss its application in training deep networks with limited labeled data. (10 marks, 2024-25)
2. Q4b. Explain the concept of semi-supervised learning with examples. Compare it with supervised and unsupervised learning. (7 marks, 2025-26)
3. Q1c. Discuss convolutional neural network (CNN)? (2 marks, 2025-26)
4. Q1c. Discuss the role of convolutional layers in Convolutional Neural Networks. (2 marks, 2024-25)
5. Q2b. Define VC dimension and discuss its implications for understanding the generalization capabilities of deep networks. (10 marks, 2024-25)
6. Q4a. Analyze the trade-offs between increasing network depth and the risk of vanishing/exploding gradients. What role does skip connections in ResNet play in addressing these issues? (10 marks, 2024-25)
7. Q2b. Derive and explain the role of batch normalization in accelerating deep neural network training. How does it help in reducing internal covariate shifts? (10 marks, 2024-25)
8. Q4a. Explain the architecture and training process of a Generative Adversarial Network. What challenges arise during training, and how can they be mitigated? (10 marks, 2024-25)
9. Q4b. Discuss the probabilistic theory behind deep learning models. How do Bayesian principles apply to the optimization and uncertainty estimation in deep networks? (10 marks, 2024-25)
10. Q4b. Demonstrate how batch normalization reduces internal covariate shift. (10 marks, 2024-25)

Other Deep Learning units

• Unit 1 Notes
• Unit 3 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 2 Important Questions
• Deep Learning Unit 2 PYQ
• Deep Learning Important Topics
• Deep Learning Predicted Paper