Deep & Reinforcement Learning Notes

CS702(B) Deep & Reinforcement Learning complete study material for RGPV CSE 7th Semester. Download unit-wise notes, important questions, PYQ analysis and exam resources for Deep Learning, Autoencoders, CNN Architectures, Reinforcement Learning, Q-Learning, DQN, Policy Gradient, Actor-Critic and Advanced RL methods.

Open Units Download PDFs Important Questions

About Deep & Reinforcement Learning

Deep & Reinforcement Learning combines neural network-based learning with decision-making methods. This subject covers deep neural networks, optimization methods, autoencoders, CNN architectures and reinforcement learning algorithms used for intelligent agents.

🧠

Deep Learning

Study neurons, activation functions, gradient descent, RNN, LSTM, GRU and attention mechanisms.

🖼️

CNN Architectures

Learn LeNet, AlexNet, VGGNet, GoogLeNet, ResNet and visualization methods.

🎮

Reinforcement Learning

Understand MDP, Bellman equation, value iteration, Q-learning, DQN and policy gradient.

Deep & Reinforcement Learning Unit-Wise Notes

Open any unit to access detailed notes, important questions and PYQ analysis.

1

Unit 1: Deep Learning Fundamentals

History of deep learning, McCulloch Pitts neuron, threshold logic, activation functions, gradient descent, Adam, RNN, BPTT, GRU, LSTM, encoder-decoder and attention mechanism.

  • Activation Functions
  • Gradient Descent
  • RNN, GRU & LSTM
Open Unit 1
2

Unit 2: Autoencoders & Regularization

Autoencoders and PCA, denoising autoencoders, sparse autoencoders, contractive autoencoders, bias-variance tradeoff, L2 regularization, dropout and normalization.

  • Autoencoders
  • Regularization
  • Dropout & Normalization
Open Unit 2
3

Unit 3: CNN Architectures

Greedy layerwise pre-training, activation functions, weight initialization, word representations, CNN, LeNet, AlexNet, ZF-Net, VGGNet, GoogLeNet, ResNet and deep learning trends.

  • CNN
  • LeNet to ResNet
  • Deep Dream & Deep Art
Open Unit 3
4

Unit 4: Reinforcement Learning Fundamentals

Introduction to RL, bandit algorithms, UCB, PAC, MDP, Bellman optimality, dynamic programming, value iteration, policy iteration, Q-learning and TD learning.

  • MDP
  • Bellman Optimality
  • Q-Learning
Open Unit 4
5

Unit 5: Advanced Reinforcement Learning

Fitted Q, Deep Q-Learning, DQN, policy gradient, actor-critic method, hierarchical RL, POMDPs, inverse reinforcement learning, maximum entropy IRL and GAIL.

  • DQN
  • Policy Gradient
  • Actor-Critic
Open Unit 5

Detailed Syllabus

Complete syllabus of CS702(B) Deep & Reinforcement Learning for RGPV CSE 7th Semester.

Unit 1

History of Deep Learning, McCulloch Pitts Neuron, Thresholding Logic, Activation Functions, Gradient Descent, Momentum Based GD, Nesterov Accelerated GD, Stochastic GD, AdaGrad, RMSProp, Adam, Eigenvalue Decomposition, RNN, BPTT, Vanishing and Exploding Gradients, Truncated BPTT, GRU, LSTMs, Encoder Decoder Models and Attention Mechanism.

Unit 2

Autoencoders and relation to PCA, regularization in autoencoders, denoising autoencoders, sparse autoencoders, contractive autoencoders, bias variance tradeoff, L2 regularization, early stopping, dataset augmentation, parameter sharing and tying, injecting noise, ensemble methods, dropout, batch normalization, instance normalization and group normalization.

Unit 3

Greedy layerwise 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 CNN, guided backpropagation, Deep Dream, Deep Art and recent trends in deep learning architectures.

Unit 4

Introduction to reinforcement learning, bandit algorithms, UCB, PAC, median elimination, policy gradient, full RL and MDPs, Bellman optimality, dynamic programming, value iteration, policy iteration, Q-learning, temporal difference methods, eligibility traces, function approximation and least squares methods.

Unit 5

Fitted Q, Deep Q-Learning, advanced Q-learning algorithms, learning policies by imitating optimal controllers, DQN and 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 and recent trends in RL architectures.

Download Study Resources

Upload PDFs in the pdfs folder using these file names.

📘

Complete Notes

Complete Deep & Reinforcement Learning notes for all units.

Download Notes

Important Questions

Most expected RGPV questions for CS702(B).

Download Questions
📄

PYQ Analysis

Previous year question analysis for better preparation.

Download PYQ

Important Questions - Deep & Reinforcement Learning

Most important questions for 7 marks and 14 marks answers.

  1. Explain history and need of Deep Learning.
  2. Explain McCulloch Pitts neuron and thresholding logic.
  3. Explain different activation functions.
  4. Explain Gradient Descent, Momentum GD and Adam optimizer.
  5. Explain RNN and Backpropagation Through Time.
  6. Explain vanishing and exploding gradient problem.
  7. Explain GRU and LSTM networks.
  8. Explain autoencoders and relation with PCA.
  9. Explain denoising, sparse and contractive autoencoders.
  10. Explain bias-variance tradeoff and L2 regularization.
  11. Explain dropout and batch normalization.
  12. Explain CNN architecture and working.
  13. Explain LeNet, AlexNet, VGGNet, GoogLeNet and ResNet.
  14. Explain reinforcement learning and MDP.
  15. Explain Bellman optimality equation.
  16. Explain value iteration and policy iteration.
  17. Explain Q-learning and Temporal Difference learning.
  18. Explain Deep Q-Learning and DQN.
  19. Explain Policy Gradient and Actor-Critic method.
  20. Explain inverse reinforcement learning and GAIL.

PYQ Analysis Table

Topic Unit Expected Frequency Importance
Activation Functions Unit 1 High ⭐⭐⭐⭐
Gradient Descent Optimizers Unit 1 Very High ⭐⭐⭐⭐⭐
RNN, BPTT, GRU, LSTM Unit 1 Very High ⭐⭐⭐⭐⭐
Autoencoders Unit 2 Very High ⭐⭐⭐⭐⭐
Regularization & Dropout Unit 2 High ⭐⭐⭐⭐
CNN Architectures Unit 3 Very High ⭐⭐⭐⭐⭐
Reinforcement Learning & MDP Unit 4 Very High ⭐⭐⭐⭐⭐
Bellman Optimality Unit 4 Very High ⭐⭐⭐⭐⭐
Q-Learning & TD Learning Unit 4 Very High ⭐⭐⭐⭐⭐
DQN, Policy Gradient, Actor-Critic Unit 5 Very High ⭐⭐⭐⭐⭐

FAQs - Deep & Reinforcement Learning

What is Deep Learning?

Deep Learning is a machine learning technique that uses multi-layer neural networks to learn complex patterns from data.

What is Reinforcement Learning?

Reinforcement Learning is a learning method where an agent learns actions by interacting with an environment and receiving rewards.

What is Q-Learning?

Q-Learning is a reinforcement learning algorithm used to learn the best action-value function for decision-making.

What is DQN?

DQN stands for Deep Q-Network. It combines Q-learning with deep neural networks.

What is Actor-Critic Method?

Actor-Critic combines policy-based and value-based learning using an actor and a critic model.

Is Deep & Reinforcement Learning scoring?

Yes, it is scoring if you prepare definitions, algorithms, architecture diagrams and comparisons properly.

Related 7th Semester Subjects

Software Architecture

Architecture models, ADLs, CBAM, ATAM, ADD and documentation.

Open Software Architecture

Computational Intelligence

Fuzzy systems, genetic algorithms, rough sets, HMM and swarm intelligence.

Open CI

Big Data

Hadoop, HDFS, MapReduce, Hive, Pig, NoSQL and social network mining.

Open Big Data

Data Mining & Warehousing

OLAP, classification, clustering, association rules, Apriori and FP Growth.

Open DMW