🧠 Artificial Intelligence Hierarchy

Artificial Intelligence (AI)
Expert Systems
  ├─ Rule-based Systems
  └─ Knowledge-based Systems

Natural Language Processing (NLP)
  ├─ Text Classification
  ├─ Named Entity Recognition (NER)
  ├─ Sentiment Analysis
  ├─ Machine Translation
  └─ Question Answering

Transformer Architecture
  ├─ Encoder-Only (BERT, RoBERTa)
  │   ├─Embedding Models ← RAG embeddings
  │   ├─MiniLM (384 dims)
  │   ├─multi-qa-mpnet (768 dims)
  │   └─OpenAI ada-002 (1536 dims)
  ├─ Decoder-Only (GPT, Claude, LLaMA)
  ├─ Large Language Models (LLMs)
  └─ Encoder-Decoder (T5, BART)

Computer Vision
  ├─ Image Classification
  ├─ Object Detection
  ├─ Image Segmentation
  ├─ Facial Recognition
  ├─ Image Recognition & Object Detection
  └─ Medical Imaging & OCR

Generative Models
  ├─ Variational Autoencoders (VAE)
  ├─ Generative Adversarial Networks (GAN)
  │   ├─ DCGAN
  │   ├─ StyleGAN
  │   └─ CycleGAN
  └─ Diffusion Models
    ├─ Stable Diffusion
    ├─ DALL-E
    └─ Midjourney

Machine Learning (ML)
  ├─ Supervised Learning
  │   ├─ Classification
  │   │   ├─ Logistic Regression
  │   │   ├─ Decision Trees
  │   │   ├─ Random Forest
  │   │   ├─ Support Vector Machines (SVM)
  │   │   ├─ Naive Bayes
  │   │   └─ K-Nearest Neighbors (KNN)
  │   └─ Regression
  │       ├─ Linear Regression
  │       ├─ Polynomial Regression
  │       └─ Ridge/Lasso Regression
  ├─ Unsupervised Learning
  │   ├─ Clustering
  │   │   ├─ K-Means
  │   │   ├─ DBSCAN
  │   │   └─ Hierarchical Clustering
  │   ├─ Dimensionality Reduction
  │   ├─ PCA (Principal Component Analysis)
  │   ├─ t-SNE
  │   └─ UMAP
  └─ Reinforcement (Q-Learning, PPO)

Deep Learning (DL)
  ├─ Feedforward Neural Networks (FNN)
  │   ├─ Perceptron
  │   └─ Multi-Layer Perceptron (MLP)
  ├─ Convolutional Neural Networks (CNN)
  │   ├─ ResNet / EfficientNet
  │   └─ YOLO (Object Detection)
  ├─ Recurrent Neural Networks (RNN)
  │   ├─ Vanilla RNN
  │   ├─ LSTM (Long Short-Term Memory)
  │   │   ├─ Bidirectional LSTM
  │   │   └─ Stacked LSTM
  │   └─ GRU (Gated Recurrent Unit)

Recurrent Neural Networks (RNN)
  ├─ Vanilla RNN
  ├─ LSTM (Long Short-Term Memory)
  │   ├─ Bidirectional LSTM
  │   └─ Stacked LSTM
  └─ GRU (Gated Recurrent Unit)

Graph Neural Networks (GNN)
  ├─ Graph Convolutional Networks (GCN)
  └─ Graph Attention Networks (GAT)

Convolutional Neural Networks (CNN)
  ├─ LeNet
  ├─ AlexNet
  ├─ VGGNet
  ├─ ResNet
  └─ EfficientNet

Robotics
  ├─ Control Algorithms
  └─ Path Planning (A*, Dijkstra)