CS-702 (B) RGPV B.Tech
Deep & Reinforcement Learning (DRL)
Previous year papers and the official syllabus are free to read, no account needed.
Previous Year Papers
2 papers, latest Jun 2025
Syllabus, notes and important questions for CS-702 (B)
Syllabus units
Topics as the official RGPV syllabus lists them.
Unit 1 Foundations of Deep Learning 21 topics
- History of Deep Learning
- McCulloch‑Pitts neuron
- Thresholding Logic
- Activation functions
- Gradient Descent (GD)
- Momentum based GD
- Nesterov accelerated GD
- Stochastic GD
- AdaGrad
- RMSProp
- Adam
- Eigenvalue Decomposition
- Recurrent Neural Networks
- Backpropagation through time (BPTT)
- Vanishing and exploding gradients
- Truncated BPTT
- Gated Recurrent Unit (GRU)
- Long Short‑Term Memory (LSTM)
- Encoder‑Decoder models
- Attention Mechanism
- Attention over images
Unit 2 Autoencoders and Regularization 16 topics
- Autoencoders and their relation to PCA
- Regularization in autoencoders
- Denoising autoencoders
- Sparse autoencoders
- Contractive autoencoders
- Bias–Variance trade‑off
- L2 regularization
- Early stopping
- Dataset augmentation
- Parameter sharing and tying
- Injecting noise at input
- Ensemble methods
- Dropout
- Batch Normalization
- Instance Normalization
- Group Normalization
Unit 3 Convolutional Architectures and Pre‑training 16 topics
- Greedy layerwise pre‑training
- Advanced activation functions
- Weight initialization methods
- Learning vector representations of words
- Convolutional Neural Networks (CNNs)
- LeNet
- AlexNet
- ZF‑Net
- VGGNet
- GoogLeNet
- ResNet
- Visualizing CNNs
- Guided backpropagation
- Deep Dream
- Deep Art
- Recent trends in deep learning architectures
Unit 4 Fundamentals of Reinforcement Learning 11 topics
- Introduction to Reinforcement Learning (RL)
- Bandit algorithms – UCB, PAC, Median Elimination
- Policy Gradient methods
- Full RL & Markov Decision Processes (MDPs)
- Bellman optimality principle
- Dynamic programming – value iteration, policy iteration
- Q‑learning
- Temporal‑Difference (TD) methods
- Eligibility traces
- Function approximation
- Least‑squares methods
Unit 5 Advanced RL Techniques 12 topics
- Fitted Q
- Deep Q‑Learning (DQN)
- Advanced Q‑learning algorithms
- Learning policies by imitating optimal controllers
- Policy Gradient algorithms for full RL
- Hierarchical RL
- Partially Observable MDPs (POMDPs)
- Actor‑Critic methods
- Inverse Reinforcement Learning
- Maximum entropy deep inverse RL
- Generative Adversarial Imitation Learning
- Recent trends in RL architectures