Deep Learning Unit 3 – Dimensionality Reduction: AKTU previous year questions
22 AKTU questions from Unit 3 (Dimensionality Reduction) asked in 2023–2026, tagged by marks, year and topic. In short: about 26 marks of every paper come from this unit; the most asked topic is Linear Dimensionality Reduction (PCA, LDA) (7 times). The latest ones are listed below; on the page you can filter them by 2-mark or long questions, topic and repeats.
Unit 3 previous year questions
- Describe the role of regularization during optimization. (2 marks, 2026, Training a ConvNet (Weight Init, Hyperparameters))
- Compare PCA and LDA. Explain how LDA maximizes class separability using scatter matrices. (7 marks, 2026, Linear Dimensionality Reduction (PCA, LDA))
- Explain convolution operation mathematically, including stride, padding, and feature maps. (7 marks, 2026, ConvNet Architectures (AlexNet, VGG, ResNet))
- Compare AlexNet, VGG, Inception, and ResNet in terms of depth, performance, and computation. (7 marks, 2026, ConvNet Architectures (AlexNet, VGG, ResNet))
- Explain the impact of weight initialization on the performance of deep networks. (2 marks, 2025, Training a ConvNet (Weight Init, Hyperparameters))
- Define Linear Discriminant Analysis (LDA). (2 marks, 2025, Linear Dimensionality Reduction (PCA, LDA))
- Discuss how batch normalization impacts the training of convolutional neural networks. (2 marks, 2025, Training a ConvNet (Weight Init, Hyperparameters))
- How autoencoders can be used to learn low-dimensional representations of data? (2 marks, 2025, Autoencoders)
- Explain how distance metrics are used in machine learning. (2 marks, 2025, Linear Dimensionality Reduction (PCA, LDA))
- Compare performance of autoencoders with traditional dimensionality reduction techniques. (2 marks, 2025, Autoencoders)
- Describe the process of hyperparameter optimization in training a ConvNet. What are the key hyperparameters, and how do they influence network performance? (10 marks, 2025, Training a ConvNet (Weight Init, Hyperparameters))
- What is the significance of the AlexNet architecture in deep learning history? (10 marks, 2025, ConvNet Architectures (AlexNet, VGG, ResNet))
Most asked Unit 3 topics
- Linear Dimensionality Reduction (PCA, LDA) – asked 7 times
- ConvNet Architectures (AlexNet, VGG, ResNet) – asked 6 times
- Training a ConvNet (Weight Init, Hyperparameters) – asked 5 times
Unit 3 question pattern
- 2-mark questions: 8 asked in 2023–2026
- 7-mark questions: 3 asked in 2023–2026
- 10-mark questions: 11 asked in 2023–2026
- About 26 marks from Unit 3 in every paper
Unit 3 questions year by year
- 2026: 4 Unit 3 questions asked (23 marks across that year's papers)
- 2025: 15 Unit 3 questions asked (102 marks across that year's papers)
- 2023: 3 Unit 3 questions asked (22 marks across that year's papers)