| Concept | Category | Key Idea |
|---|
| Linear Regression | Supervised Learning | Predict continuous values from linear relationships |
| Logistic Regression | Supervised Learning | Binary classification using sigmoid function |
| Decision Trees | Supervised Learning | Tree-based model with if-then rules |
| Random Forest | Supervised Learning | Ensemble of decision trees |
| SVM | Supervised Learning | Finds optimal hyperplane for classification |
| K-Means | Unsupervised Learning | Partitions data into K clusters |
| PCA | Unsupervised Learning | Dimensionality reduction via variance maximization |
| CNN | Deep Learning | Convolutional layers for image processing |
| RNN/LSTM | Deep Learning | Recurrent networks for sequential data |
| Transformer | Deep Learning | Attention-based architecture for sequences |
| Q-Learning | Reinforcement Learning | Learn action values through experience |
| AGI | Artificial General Intelligence — human-level AI |
| ANN | Artificial Neural Network |
| CNN | Convolutional Neural Network |
| CSP | Constraint Satisfaction Problem |
| FOL | First-Order Logic |
| GAN | Generative Adversarial Network |
| GPU | Graphics Processing Unit (used for AI training) |
| LLM | Large Language Model |
| ML | Machine Learning |
| NLP | Natural Language Processing |
| RAG | Retrieval-Augmented Generation |
| RL | Reinforcement Learning |
| RNN | Recurrent Neural Network |
| TPU | Tensor Processing Unit (Google's AI chip) |
| XAI | Explainable Artificial Intelligence |