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?

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

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?

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