Deep & Reinforcement Learning (CS-702 (B)) - Important Questions

What is the significance of gradient descent in training deep learning models? Discuss various optimization algorithms including AdaGrad, RMSProp, and Adam.

Describe the challenges of vanishing and exploding gradients in Recurrent Neural Networks (RNNs). How do GRUs and LSTMs mitigate these issues?

Draw and explain McCulloch Pitts neuron Model.

What are Recurrent Neural Networks?

Explain LSTM (Long Short Term Memory).

Compare and differentiate Deep vs Shallow neural networks.

What is deep learning? Explain its history, uses and applications.

What is PCA (Principle Component Analysis ) and RNN?

Explain the role of regularization techniques in deep learning. How do dropout and batch normalization contribute to improved model performance?

Explain sparse and contractive auto encoders.

Discuss the concept of greedy layerwise pre-training. What are some better activation functions introduced in recent years?

How do visualization techniques like Deep Dream and Guided Backpropagation help in understanding neural networks?

Draw and explain the architecture of convolutional network.

Explain Better Weight Initialization Methods.

Define the Policy Gradient method in reinforcement learning. How does it differ from Q-learning?

Discuss Bandit Algorithms in details.

Explain the Q Function and Q Learning Algorithm.

Explain value iteration, policy iteration and Temporal Difference Learning.

Compare the Actor-Critic method with traditional reinforcement learning techniques and explain its advantages.

Discuss recent trends in reinforcement learning architectures, including Generative Adversarial Imitation Learning.

Explain Policy Gradient Algorithm for Full RL.

Write short notes on Face Recognition application, Actor-Critic Method, and Group Normalization.

What is semi - supervised learning ?