Course Progression¶
If you would like a smooth transition in learning deep learning concepts, you need to follow the materials in a sequential order. Some sections are still pending as I am working on them, and they will have the 
icon beside them.
1. Practical Deep Learning with PyTorch¶
- Matrices
- Gradients
- Linear Regression
- Logistic Regression
- Feedforward Neural Networks (FNN)
- Convolutional Neural Networks (CNN)
- Recurrent Neural Networks (RNN)
- Long Short Term Memory Neural Networks (LSTM)
- Autoencoders (AE)
- Fully-connected Overcomplete Autoencoder (AE)
- Variational Autoencoders (VAE)
- Adversarial Autoencoders (AAE)
- Generative Adversarial Networks (GAN)
- Transformers
2. Improving Deep Learning Models with PyTorch¶
- Derivatives, Gradients and Jacobian
- Gradient Descent and Backpropagation (From Scratch FNN Regression)
- Learning Rate Scheduling
- Optimizers
- Advanced Learning Rate Optimization
- Weight Initializations and Activation Functions
- Overfitting Prevention
- Loss, Accuracy and Weight Visualizations
- Data Preprocessing for Images and Videos
- Data Preprocessing for Time Series
3. Deep Reinforcement Learning with PyTorch¶
- Supervised Learning to Reinforcement Learning
- Markov Decision Processes and Bellman Equations
- Dynamic Programming
- Monte Carlo Approach
- Temporal-Difference
- Policy Gradient: REINFORCE
- Policy Gradient: Actor-Critic
- Policy Gradient: A2C/A3C
- Policy Gradient: ACKTR
- Policy Gradient: PPO
- Policy Gradient: DPG
- Policy Gradient: DDPG (DQN & DPG)
4. From Scratch with Python and PyTorch¶
- From Scratch Logistic Regression Classification
- From Scratch FNN Classification
- From Scratch CNN Classification
- From Scratch RNN Classification
- From Scratch LSTM Classification
- From Scratch AE
5. Large Language Models with PyTorch¶
- Introduction
- What is Temperature