Deep Learning Unit 2 – Deep Networks: important questions for AKTU
Unit 2 (Deep Networks) questions that AKTU repeats most often. This unit carries about 38 marks per paper. Start with the repeated questions, then the most asked topics.
Most repeated Unit 2 questions
- Explain the concept of semi-supervised learning with examples. Compare it with supervised and unsupervised learning. (7 marks, 2026, Semi-supervised Learning) – also asked in 2025
- How does semi-supervised learning differ from supervised and unsupervised learning? Discuss its application in training deep networks with limited labeled data. (10 marks, 2025, Semi-supervised Learning) – also asked in 2026
- Discuss convolutional neural network (CNN)? (2 marks, 2026, Convolutional Networks) – also asked in 2025
Most important Unit 2 topic
- Convolutional Networks (Unit 2: Deep Networks) – asked 9 times in 2023, 2025, 2026
Most asked Unit 2 topics
- Convolutional Networks – asked 9 times
- History & Theory of Deep Learning – asked 8 times
- Regularization & Batch Normalization – asked 4 times
More Unit 2 previous year questions
- Name any two activation functions used in deep networks. (2 marks, 2026, Convolutional Networks)
- Name two applications of Word2Vec. (2 marks, 2026, Generative Adversarial Networks (GAN))
- Describe how probabilistic models help reduce overfitting. Explain with examples. (7 marks, 2026, Regularization & Batch Normalization)
- Compare batch normalization with layer normalization and instance normalization. (7 marks, 2026, Regularization & Batch Normalization)
- Explain the significance of the “AI Winter” in deep learning history. (2 marks, 2025, History & Theory of Deep Learning)
Unit 2 syllabus topics
- History & Theory of Deep Learning
- Regularization & Batch Normalization
- Convolutional Networks
- Generative Adversarial Networks (GAN)
- Semi-supervised Learning