Important RGPV Question
AL 503 (B) Deep Learning
V Sem, AIML
UNIT 1-Introduction History of Deep Learning
Q.1) Explain the historical progression of Deep Learning, highlighting key milestones and breakthroughs that have shaped its development.
(RGPV Nov 2023)
Q.2) Assess the representation power of Multilayer Perceptrons (MLPs) and discuss their capacity to learn complex relationships in data.
(RGPV Nov 2023)
Q.3) Discuss the Backpropagation algorithm and its role in optimizing the weights of neural networks during the training process.
(RGPV Nov 2023)
Q.4) Discuss the GPU implementation of randomized SVD and write its applications.
(RGPV Nov 2022)
Q.5) What is the representation power of a multilayer network of sigmoid neurons? Explain in detail.
(RGPV Nov 2022)
Q.6) What is batch normalization? Explain how does it work and also write its advantages.
(RGPV Nov 2022)
UNIT 2-Deep Feedforward Neural Networks
Q.1) Investigate the theoretical foundations and practical implications of AdaGrad, Adam, and RMSProp optimization algorithms in the context of training deep neural networks.
(RGPV Nov 2023)
Q.2) 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.
(RGPV Nov 2023)
Q.3) ) Discuss the role of regularization in auto-encoders and its impact on the training process.
(RGPV Nov 2023)
Q.4) Discuss the challenges associated with encoding and decoding sequential data and how RNNs handle these challenges through their inherent architecture.
(RGPV Nov 2023)
Q.5) Explain in brief sparse auto-encoder and contractive auto- encoder.
(RGPV Nov 2022)
Q.6) Write a short note on regularization of auto encoders.
(RGPV Nov 2022)
Q.7) When should auto encoders be used instead of PCA/SVD for dimensionality reduction? Justify.
(RGPV Nov 2022)
UNIT 3- Introduction to Convolutional neural Networks
Q.1) Explain the concept of Convolutional Neural Networks (CNNs) and their role in image recognition tasks.
(RGPV Nov 2023)
Q.2) Define the ReLU activation function and explain its significance in CNNs.
(RGPV Nov 2023)
Q.3) Explain the concept of Deep Dream and its role in generating surreal images based on neural network activations.
(RGPV Nov 2023)
Q.4) Discuss in detail about ReLu activation function.
(RGPV Nov 2022)
Q.5) Illustrate the CNN terms Padding and Pooling.
(RGPV Nov 2022)
Q.6) What is unit pruning? Discuss the need of unit pruning in deep learning.
(RGPV Nov 2022)
UNIT 4- Introduction to Deep Recurrent Neural Networks
Q.1) Explain the fundamental concepts and various architectures of Deep Recurrent Neural Networks (RNNs).
(RGPV Nov 2023)
Q.2) Explain the challenges of vanishing and exploding gradients during the BPTT process and their impact on the network’s ability to learn long-range dependencies.
(RGPV Nov 2023)
Q.3) Explain briefly about directed graphical model.
(RGPV Nov 2022)
Q.4) Explain briefly deep recurrent neural networks and its architecture with a neat diagram.
(RGPV Nov 2022)
Q.5) Discuss in detail Long Short Term Memory (LSTM) and write the advantages of LSTM.
(RGPV Nov 2022)
UNIT 5-Introduction to Deep Generative Models
Q.1) Explain the concept of value iteration in dynamic programming for solving Markov Decision Processes (MDPs).
(RGPV Nov 2023)
Q.2) Explain briefly about the following auto regressive models.
a) NADE
b) MADE
(RGPV Nov 2022)
EXTRA QUESTIONS-
Q.1) Compare and contrast policy iteration with value iteration in terms of convergence and computational complexity.
(RGPV Nov 2023)
Q.2) Compare and contrast different least squares methods, such as LSPI (Least Squares Policy Iteration).
(RGPV Nov 2023)
Q.3) Explore advanced Q-learning algorithms, such as Double DQN and Dueling DQN.
(RGPV Nov 2023)
Q.4) Write a short note on any two of the following:
a) Representation learning.
b) Feed forward neural network
c) Weight decay and also the benefits of using weight decay
d) Deep belief networks
(RGPV Nov 2022)
— Best of Luck for Exam —
