AL503 (B) - Deep Learning

Explain the difference between supervised and unsupervised learning. Provide examples where deep learning can be used for each type.

What are activation functions? Why are they important in neural networks? List and explain different types of activation functions used in deep learning.

Briefly explain the architecture of a simple neural network. What are activation functions and why are they used? Discuss the role of back propagation in training neural networks.

Define the terms "Overfitting" and "Underfitting" in the context of deep learning models. What techniques can be used to prevent overfitting?

What is the Vanishing Gradient Problem? How does it affect the training of deep neural networks and what strategies can be used to mitigate it?

What is a Recurrent Neural Network (RNN), and how is it useful for sequence data? Compare it with a traditional feed-forward neural network.

Discuss the role of dropout in training deep neural networks. How does it help improve generalization?

Explain the backpropagation algorithm. How is it used to update the weights in a neural network during training?

Develop A table with examples of different formats of data that can be used with convolutional network system.

What is batch normalization and why is it used during the training of deep networks?

What is the difference between normalization and standardization in data preprocessing?

Discuss unsupervised learning with examples.

Explain how reinforcement learning differs from supervised learning and provide an example of how deep learning can be applied in reinforcement learning.

Discuss the differences between Generative Adversarial Networks (GANs) and Variational Autoencoders (VAEs). When would you choose one over the other?

Explain the working of any two of the following machine learning algorithms in detail:

i) Long Short-Term Memory Networks (LSTM)

ii) Logistic Regression

iii) Recursive Neural Networks