CY-802 (B) RGPV B.Tech
Deep & Reinforcement Learning (DRL)
The official syllabus is free to read, no account needed.
Syllabus, notes and important questions for CY-802 (B)
- Syllabus Official RGPV syllabus Free
- Important Questions 6 sets of questions Free
- Notes 5 documents Free
- Previous Year Papers None for CY-802 (B) yet
Syllabus units
Topics as the official RGPV syllabus lists them.
Unit 1 History of Deep Learning 21 topics
- History of Deep Learning
- McCulloch-Pitts Neuron
- Thresholding Logic
- Activation functions
- Gradient Descent ($\mathrm{GD}$)
- Momentum-based GD
- Nesterov Accelerated GD
- Stochastic GD
- AdaGrad
- RMSProp
- Adam
- Eigenvalue Decomposition
- Recurrent Neural Networks
- Back propagation through time (BPTT)
- Vanishing and Exploding Gradients
- Truncated BPTT
- GRU
- LSTMs
- Encoder-Decoder Models
- Attention Mechanism
- Attention over images
Unit 2 Autoencoders and relation to PCA 16 topics
- Autoencoders and relation to PCA
- Regularization in autoencoders
- Denoising autoencoders
- Sparse autoencoders
- Contractive autoencoders
- Bias-Variance Tradeoff
- $L_{2}$ regularization
- Early stopping
- Dataset augmentation
- Parameter sharing and tying
- Injecting noise at input
- Ensemble methods
- Dropout
- Batch Normalization
- Instance Normalization
- Group Normalization
Unit 3 Greedy Layer-wise Pre-training 16 topics
- Greedy layer-wise pre-training
- Better activation functions
- Better weight initialization methods
- Learning vectorial representations of words
- Convolutional Neural Networks
- LeNet
- AlexNet
- ZF-Net
- VGGNet
- GoogLeNet
- ResNet
- Visualizing convolutional neural networks
- Guided back propagation
- Deep Dream
- Deep Art
- Recent trends in deep learning architectures
Unit 4 Introduction to Reinforcement Learning (RL) 12 topics
- Introduction to reinforcement learning (RL)
- Bandit algorithms – UCB, PAC, Median Elimination
- Policy Gradient
- Full RL & MDPs
- Bellman Optimality
- Dynamic Programming – Value iteration
- Policy iteration
- Q-learning & Temporal Difference Methods
- Temporal-Difference Learning
- Eligibility Traces
- Function Approximation
- Least Squares Methods
Unit 5 Advanced Q-Learning and RL Architectures 13 topics
- Fitted Q
- Deep Q-Learning
- Advanced Q-learning algorithms
- Learning policies by imitating optimal controllers
- DQN & Policy Gradient
- Policy Gradient algorithms for full RL
- Hierarchical RL
- POMDPs
- Actor-Critic Method
- Inverse reinforcement learning
- Maximum Entropy Deep Inverse Reinforcement Learning
- Generative Adversarial Imitation Learning
- Recent trends in RL architectures