Deep Learning Unit 1 Notes AKTU (BAI701)

Unit 1: Introduction to Neural Networks – AKTU syllabus topics

• Introduction to Machine Learning
• Linear Models (SVM, Perceptron, Logistic Regression)
• Neural Networks & Shallow Networks
• Training a Network (Loss, Backprop, SGD)
• Universal Function Approximation

Most asked AKTU PYQ questions from Unit 1

1. Q3b. Discuss the relationship between the choice of activation function in a shallow neural network and its ability to model non-linear relationships. (10 marks, 2024-25)
2. Q3a. Prove that neural networks can act as universal function approximators. Discuss any constraints or assumptions involved in this theorem. (10 marks, 2024-25)
3. Q2a. Derive the gradient of the logistic regression loss function with respect to its parameters. How does regularization impact its optimization process? (10 marks, 2024-25)
4. Q3a. Explain the concept of stochastic gradient descent (SGD). How does it differ from batch and mini-batch gradient descent in terms of computational efficiency and convergence? (10 marks, 2024-25)
5. Q3b. Compare and contrast the theoretical underpinnings of perceptrons and logistic regression in the context of binary classification problems. (10 marks, 2024-25)
6. Q2a. Explain the mathematical foundation of the Support Vector Machine (SVM) algorithm and describe its kernel trick for non-linear classification problems. How does it differ from logistic regression? (10 marks, 2024-25)
7. Q3a. Explain the purpose of backpropagation in training neural networks. (10 marks, 2024-25)
8. Q3b. Describe the role of stochastic gradient descent (SGD) in optimization. (10 marks, 2024-25)
9. Q2a. Illustrate how activation functions like ReLU and Sigmoid work in a shallow network. (10 marks, 2024-25)
10. Q5a. Explain Back propagation with its algorithm. (10 marks, 2022-23)

Other Deep Learning units

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