/AI_Basics

AI Basic Implementations

Primary LanguageJupyter Notebook

AI_Basics

AI Basic Implementations

Contents

  1. Basics
    • 1-1. Basics of Python
    • 1-2. Basics of Numpy
    • 1-3. Introduction to PyTorch
  2. Multi-Layer Perceptron (MLP) and Model Selection
    • 2-1. MLP
    • 2-2. k-fold cross validation
  3. CNNs
    • 3-1. Simple CNN (basic)
    • 3-2. ResNet (with torchvision)
    • 3-3. Simple CNN (Scratch)
    • 3-4. Simple CNN with k-fold cross validation (Scratch)
    • 3-5. MobileNet, EfficeintNet (Scratch)
  4. GNNs
    • 4-1. GNN - Graph Classification Task
    • 4-2. GNN - Node Classification Task
  5. RNNs
    • 5-1. Simple RNN (Basic)
    • 5-2. LSTM
    • 5-3. LSTM, Seq2Seq (Scratch)
    • 5-4. Text Classification Model with RNN, GRU
  6. Generative Models
    • 6-1. Variational Autoencoder (VAE)
    • 6-2. Generative Adversarial Network (GAN)
  7. Transformers
    • 7-1. Transformer (Scratch)
    • 7-2. Transformer (hugging-face)
    • 7-3. BERT fine-tuning
  8. Distributed Learning (Ray, DP, DDP)
    • 8-1. Distributed Learning
    • 8-2. Ray