Site map
AI Encyclopedia
Every AI concept, one page each, by category. 312 entries.
Also assitemap.xmlllms.txtllms-full.txtOKF site index
Start hereAI Encyclopedia
Core ML Concepts · 49
- Artificial Intelligence (AI)
- Machine Learning (ML)
- Supervised Learning
- Unsupervised Learning
- Neural Network
- Deep Learning
- Features & Labels
- Overfitting & Underfitting
- Classification vs Regression
- Training vs Inference
- Linear Regression
- Data · The Fuel of AI
- Decision Trees & Random Forests
- Evaluation Metrics & Cross-Validation
- Symbolic AI & Expert Systems
- Logistic Regression
- Exploratory Data Analysis (EDA)
- k-Nearest Neighbors (kNN)
- Naive Bayes
- Data Science vs ML vs AI
- Narrow AI vs Strong AI
- Clustering
- Data Labeling
- History of AI
- Bias-Variance Tradeoff
- Transfer Learning
- Regularization
- Few-Shot & Zero-Shot Learning
- Semi-Supervised Learning
- Time Series Forecasting
- Support Vector Machines (SVM)
- Data Leakage
- Data Augmentation
- Ensemble Learning
- Dropout
- Knowledge Representation & Reasoning
- Active Learning
- Data-Centric AI
- Data Quality for AI
- Datasheets, Data Cards and Model Cards
- Survival Analysis
- Curriculum Learning
- Self-Supervised Learning
- Continual Learning & Catastrophic Forgetting
- Meta-Learning (Learning to Learn)
- Causal Inference & ML
- Data Hardness and Example Difficulty
- Hard Negative Mining
- Reward Models and Process Reward Models
Math & Optimization · 28
- Gradient Descent
- Loss Function
- Activation Functions
- K-Means Clustering
- Linear Algebra for ML
- Probability & Bayes' Theorem
- Statistics for ML
- Search Algorithms (A*, Minimax)
- Backpropagation
- Embeddings
- Dimensionality Reduction
- Feature Engineering
- Anomaly Detection
- Boosting (XGBoost, LightGBM)
- Information Theory: Entropy & KL Divergence
- Optimizers: SGD, Momentum & Adam
- Evolutionary & Swarm Optimization
- Latent Space
- Calculus for ML
- Fuzzy Logic
- Game Theory for AI
- Bayesian ML & Uncertainty
- Monte Carlo Methods
- Probabilistic Graphical Models & HMMs
- Double Descent
- Grokking
- The Lottery Ticket Hypothesis
- Gaussian Processes
Architectures · 31
- Multilayer Perceptron (MLP)
- Transformer Architecture
- Attention Mechanism
- Self-Attention
- Convolutional Neural Network (CNN)
- Recurrent Neural Network (RNN)
- LSTM (Long Short-Term Memory)
- GPT (Generative Pre-trained Transformer)
- BERT (Bidirectional Encoder)
- Residual Connections & ResNet
- Normalization Layers (BatchNorm to RMSNorm)
- Autoencoders
- Encoder-Decoder Models
- Gated Recurrent Unit (GRU)
- Model Merging
- State Space Models (Mamba)
- Vision Transformer (ViT)
- Multimodal Models
- Knowledge Distillation
- Model Quantization & Compression
- Neural Architecture Search (NAS)
- Neuro-Symbolic AI
- Mixture-of-Experts (MoE)
- Graph Neural Networks (GNNs)
- Positional Encoding & RoPE
- Boltzmann Machines
- Spiking Networks & Neuromorphic Computing
- FlashAttention and IO-Aware Attention
- GQA, MQA, Multi-head Latent and Sliding Window Attention
- Diffusion Language Models
- Pruning and Sparsity
NLP & Language · 43
- Natural Language Processing (NLP)
- Tokenization
- Prompt Engineering
- Sentiment Analysis
- Bag-of-Words & TF-IDF
- Large Language Models (LLMs)
- Token Density and Information Density
- Topic Density and Topical Coverage
- Prompt and Context Compression
- Word2Vec & Word Embeddings
- Retrieval-Augmented Generation (RAG)
- Chain-of-Thought Reasoning
- Vector Databases
- Context Window & Long Context
- Text Generation & Sampling
- Machine Translation
- Named Entity Recognition (NER)
- Reasoning Models & Test-Time Compute
- Context Engineering
- Speech Recognition (ASR) & Whisper
- LoRA & Parameter-Efficient Fine-Tuning
- Open-Weights & Small Language Models
- Text Summarization
- Topic Modeling
- Information Extraction
- Semantic Search
- Hybrid Search & Reranking
- Chunking
- Knowledge Graphs
- Structured Outputs
- Question Answering
- NLP Metrics (BLEU, ROUGE)
- Semantic Caching
- Text-to-SQL and Natural Language Querying
- Agentic RAG
- Fine-Tuning LLMs
- LLM Scaling Laws
- RLHF (Reinforcement Learning from Human Feedback)
- DPO & Preference Optimization
- GraphRAG
- Data Deduplication and Pruning
- Pretraining Data and Data Mixtures
- ColBERT and Late Interaction Retrieval
Computer Vision · 11
Generative AI · 16
- Generative AI
- Foundation Models
- Synthetic Data
- Stable Diffusion & Text-to-Image
- Voice Cloning & TTS
- AI Music Generation
- AI Code Generation
- AI Image Editing & Inpainting
- Diffusion Models
- GANs (Generative Adversarial Networks)
- VAEs (Variational Autoencoders)
- Text-to-Video Generation
- 3D Generation & NeRFs
- Flow Matching & Modern Diffusion
- Speech-to-Speech and Realtime Voice Models
- Any-to-Any (Omni) Models
Reinforcement Learning · 14
- Reinforcement Learning (RL)
- Q-Learning & Deep Q-Networks (DQN)
- Markov Decision Process (MDP)
- Policy Gradient & Actor-Critic
- PPO (Proximal Policy Optimization)
- Reward Design & Reward Hacking
- Multi-Agent Reinforcement Learning
- World Models
- Sim-to-Real Transfer
- Inverse Reinforcement Learning
- GRPO (Group Relative Policy Optimization)
- Imitation Learning
- Offline Reinforcement Learning
- AlphaZero and MuZero
MLOps & Infrastructure · 34
- GPU & TPU Computing
- Experiment Tracking
- The AI Stack
- ML Frameworks (PyTorch, TensorFlow, JAX)
- AI Platforms
- AI Energy & Environmental Impact
- Batch vs Online Inference
- Model Deployment & Serving
- MLOps (ML Operations)
- Data Pipelines & ETL
- Edge AI & On-Device ML
- Model Versioning & Registry
- ML Monitoring & Observability
- LLM Evaluation & Benchmarks
- Hyperparameter Tuning
- AI Data Centers & the AI Factory
- Inference Cost & Token Economics
- Digital Twins
- Prompt Caching
- LLMOps
- Model Routing & AI Gateways
- Feature Stores
- Model & Data Drift
- AutoML
- A/B Testing for ML
- Ablation Studies
- Offline and Online Evaluation
- Federated Learning
- Distributed Training
- Inference Optimization
- Quantum Machine Learning
- Numerical Precision & Mixed-Precision Training
- Confidential Computing
- Gradient Checkpointing and Memory-Efficient Training
AI Agents & Applications · 36
- AI for Creative Industries
- Enterprise AI
- Vibe Coding
- Agentic AI
- AI in Marketing & Search
- AI in Education
- AI for Science
- AI for Climate, Weather and Materials
- Levels of Agent Autonomy
- Agentic Commerce and Payments
- AI Agents
- Tool Use & Function Calling
- Recommendation Systems
- Explainable AI (XAI)
- AI-Powered Search & Ranking
- Conversational AI & Chatbots
- Model Context Protocol (MCP)
- Computer Use & Browser Agents
- Agentic Coding
- Multi-Agent Systems & Orchestration
- Physical AI & Robotics
- Agent Evaluation
- Agent Skills
- Automated Planning
- Agentic Workflows & Patterns
- AI in Cybersecurity
- AI in Finance
- Voice Agents
- Autonomous Vehicles & Robotics
- AI-Driven Drug Discovery
- AI in Healthcare & Medical Imaging
- Vision-Language-Action Models
- Agent Memory, Planning & Reflection
- Agent Harnesses & Scaffolding
- Agent-to-Agent Protocols (A2A)
- Cognitive Architectures
Safety, Ethics & Governance · 33
- AI Hallucinations
- AI Regulation & Governance
- AI Safety
- Responsible AI
- Human in the Loop
- AI Governance
- AI Ethics
- AI Risk Management
- Model Specs and Behavior Policies
- AI Incidents and Incident Databases
- Children, Teens and AI
- AI, Elections and Information Integrity
- US AI Policy and Executive Orders
- Data Protection Law and AI (GDPR and beyond)
- AI Alignment
- AI Bias & Fairness
- Red Teaming AI Systems
- Prompt Injection & Jailbreaking
- AI Watermarking & Content Detection
- AGI (Artificial General Intelligence)
- Superintelligence (ASI)
- Technological Singularity
- AI Guardrails
- Data Poisoning
- Frontier Safety Frameworks
- Mechanistic Interpretability
- Constitutional AI & RLAIF
- Differential Privacy & ML Privacy
- Adversarial Machine Learning
- Deceptive Alignment & Scheming
- ARC-AGI and Reasoning Benchmarks
- Scalable Oversight
- Existential Risk from AI
Business & Strategy · 16
- AI Strategy
- Build, Buy or Partner
- AI Maturity Models
- AI Center of Excellence and Operating Model
- Data Strategy for AI
- AI Policy and Acceptable Use
- AI and the Future of Work
- AI in Sales and Customer Support
- AI in Retail, Supply Chain and Manufacturing
- Evaluating AI Vendors and Procurement
- AI Product Management
- Designing AI Products (Human-AI Interaction)
- AI Adoption and Change Management
- Measuring AI Value and ROI
- AI, Copyright and Training Data
- AI in Law and Legal Work