1. What is the difference between Batch Normalization and Layer Normalization? How do they impact training? 2. Explain the concept of attention mechanism in neural networks. How is it used in transformer models? 3. What are GANs (Generative Adversarial Networks), and how do they work? 4. Describe the concept of transfer learning. When and how would you use it? 5. What is the difference between Markov Chains and Hidden Markov Models? Provide examples of their applications. 6. How does the backpropagation algorithm work in neural networks? 7. What are the key differences between L1 and L2 regularization? In which scenarios would you use each? 8. Explain the working of a convolutional neural network (CNN). What are its primary components? 9. How does a recurrent neural network (RNN) handle sequential data? Explain vanishing and exploding gradients in RNNs. 10. Describe the process of gradient descent. What are some variations, and when would you use them?
