CY-802 (B) Deep & Reinforcement Learning Notes
5 notes for Deep & Reinforcement Learning, unit by unit.
Notes for CY-802 (B)
- Unit 1 · Short notes History of Deep Learning History of Deep Learning · McCulloch-Pitts Neuron · Thresholding Logic · Activation functions · Gradient Descent ($\mathrm{GD}$) · Momentum-based GD
- Unit 2 · Short notes Autoencoders and relation to PCA Autoencoders and relation to PCA · Regularization in autoencoders · Denoising autoencoders · Sparse autoencoders · Contractive autoencoders · Bias-Variance Tradeoff
- Unit 3 · Short notes Greedy Layer-wise Pre-training Greedy layer-wise pre-training · Better activation functions · Better weight initialization methods · Learning vectorial representations of words · Convolutional Neural Networks · LeNet
- Unit 4 · Short notes Introduction to Reinforcement Learning (RL) Introduction to reinforcement learning (RL) · Bandit algorithms – UCB, PAC, Median Elimination · Policy Gradient · Full RL & MDPs · Bellman Optimality · Dynamic Programming – Value iteration
- Unit 5 · Short notes Advanced Q-Learning and RL Architectures Fitted Q · Deep Q-Learning · Advanced Q-learning algorithms · Learning policies by imitating optimal controllers · DQN & Policy Gradient · Policy Gradient algorithms for full RL
More for CY-802 (B)
- Syllabus Official RGPV syllabus Free
- Important Questions 6 sets of questions Free
- Previous Year Papers None for CY-802 (B) yet
Other 8th semester CY subjects
- CY-801 Hardware Security
- CY-802 (A) Database Security
- CY-802 (C) Lightweight Cryptography
- CY-803 (A) Mobile and Wireless Security
- CY-803 (B) Financial crime, Motivations and Typologies
- CY-803 (C) Human Computer Interaction