AL503 (B) - Deep Learning

Explain the historical progression of Deep Learning, highlighting key milestones and breakthroughs that have shaped its development.

Assess the representation power of Multilayer Perceptrons (MLPs) and discuss their capacity to learn complex relationships in data.

Explain the architecture and working principles of Deep Feed forward Neural Networks. Discuss their application areas and key advantages over other types of neural networks.

Investigate the theoretical foundations and practical implications of AdaGrad, Adam, and RMSProp optimization algorithms in the context of training deep neural networks.

Explain the concept of Convolutional Neural Networks (CNNs) and their role in image recognition tasks.

Define the ReLU activation function and explain its significance in CNNs.

Explain the fundamental concepts and various architectures of Deep Recurrent Neural Networks (RNNs).

Explain the concept of value iteration in dynamic programming for solving Markov Decision Processes (MDPs).

Compare and contrast deep learning value iteration with value iteration in terms of convergence and computational complexity.

Discuss the Backpropagation algorithm and its role in optimizing the weights of neural networks during the training process.

Discuss the role of regularization in auto-encoders and its impact on the training process.

Explain the concept of Deep Dream and its role in generating surreal images based on neural network activations.

Discuss the challenges associated with encoding and decoding sequential data and how RNNs handle these challenges through their inherent architecture.

Compare and contrast different least squares methods, such as LSPI (Least Squares Policy Iteration).

Explore advanced Q-learning algorithms, such as Double DQN and Dueling DQN.