Artificial Intelligence (AI)

A structured overview of how modern AI is organized, from symbolic systems and classical machine learning to deep learning families (CNN, RNN, Transformer, GNN) and the generative models built on top of them. The highlighted branch traces the components used in retrieval-augmented generation.

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)

└─ Graph Neural Networks (GNN)

├─ Graph Convolutional Networks (GCN)

└─ Graph Attention Networks (GAT)

Robotics

├─ Control Algorithms

└─ Path Planning (A*, Dijkstra)

Artificial Intelligence — Hierarchy of Subfields