AI Glossary
A comprehensive guide to artificial intelligence terminology. 30 essential terms explained clearly.
Artificial Intelligence (AI)
The simulation of human intelligence by computer systems. AI encompasses machine learning, natural language processing, computer vision, and other technologies that enable machines to perform tasks that typically require human intelligence.
Machine Learning (ML)
A subset of AI where systems learn and improve from experience without being explicitly programmed. ML algorithms build mathematical models from training data to make predictions or decisions.
Deep Learning
A subset of machine learning using artificial neural networks with multiple layers (hence "deep"). Deep learning excels at pattern recognition in unstructured data like images, audio, and text.
Large Language Model (LLM)
An AI model trained on massive text datasets that can understand and generate human language. Examples include GPT-4, Claude, Gemini, and LLaMA. LLMs power chatbots, content generation, and code assistants.
Natural Language Processing (NLP)
The branch of AI focused on enabling computers to understand, interpret, and generate human language. NLP powers translation, sentiment analysis, chatbots, and search engines.
Generative AI
AI systems that can create new content — text, images, music, video, or code — based on patterns learned from training data. ChatGPT, DALL-E, and Midjourney are popular generative AI tools.
Neural Network
A computing system inspired by biological neural networks. Composed of interconnected nodes (neurons) organized in layers, neural networks learn to recognize patterns by adjusting connection weights during training.
AGI (Artificial General Intelligence)
Hypothetical AI that matches or exceeds human cognitive abilities across all domains. Unlike current narrow AI that excels at specific tasks, AGI would reason, learn, and adapt like a human.
Computer Vision
The field of AI that enables computers to interpret and understand visual information from images and videos. Applications include facial recognition, autonomous vehicles, and medical imaging.
Transformer
A neural network architecture introduced in 2017 that revolutionized NLP. Transformers use self-attention mechanisms to process sequences in parallel, enabling the training of very large language models.
Fine-Tuning
The process of taking a pre-trained AI model and training it further on a specific dataset to specialize its capabilities for a particular task or domain.
Prompt Engineering
The practice of designing and optimizing input prompts to get better outputs from AI models. Effective prompting can dramatically improve the quality and relevance of AI-generated responses.
AI Agent
An AI system that can autonomously plan and execute multi-step tasks. Unlike simple chatbots, agents can use tools, browse the web, write code, and complete complex workflows with minimal human intervention.
RAG (Retrieval-Augmented Generation)
A technique that combines information retrieval with text generation. RAG systems search a knowledge base for relevant information before generating a response, reducing hallucinations and improving accuracy.
Hallucination
When an AI model generates information that sounds plausible but is factually incorrect or fabricated. Hallucinations are a key challenge in deploying LLMs for high-stakes applications.
Token
The basic unit of text that language models process. A token can be a word, part of a word, or a character. Model pricing and context limits are typically measured in tokens.
Context Window
The maximum amount of text (measured in tokens) that a language model can process in a single interaction. Larger context windows allow models to handle longer documents and conversations.
Inference
The process of using a trained AI model to make predictions or generate outputs on new data. Inference costs (compute required to run the model) are a key factor in AI deployment economics.
Training Data
The dataset used to train an AI model. The quality, size, and diversity of training data significantly impact model performance. Data sourcing and curation are major challenges in AI development.
Multimodal AI
AI systems that can process and generate multiple types of data — text, images, audio, and video — within a single model. GPT-4V, Gemini, and Claude are examples of multimodal models.
Edge AI
Running AI models directly on local devices (phones, IoT sensors, vehicles) rather than in the cloud. Edge AI reduces latency, improves privacy, and enables AI in environments without internet connectivity.
AI Ethics
The field studying moral implications of AI systems, including bias, fairness, transparency, accountability, and societal impact. AI ethics guides responsible development and deployment of AI technologies.
Reinforcement Learning (RL)
A machine learning approach where an agent learns to make decisions by receiving rewards or penalties for its actions. RL is used in game-playing AI, robotics, and fine-tuning language models (RLHF).
RLHF (Reinforcement Learning from Human Feedback)
A technique for aligning AI models with human preferences. Human evaluators rank model outputs, and these rankings are used to train a reward model that guides further optimization. Used by ChatGPT and Claude.
API (Application Programming Interface)
In the AI context, APIs allow developers to access AI model capabilities programmatically. OpenAI, Anthropic, and Google offer APIs that enable businesses to integrate AI into their applications.
Open Source AI
AI models and tools released with open licenses, allowing anyone to use, modify, and distribute them. Notable examples include Meta's LLaMA, Mistral, and Stability AI's Stable Diffusion.
Foundation Model
A large AI model trained on broad data that can be adapted for many downstream tasks. Foundation models like GPT-4 and Claude serve as the base for chatbots, coding assistants, and specialized applications.
Embedding
A numerical representation of data (text, images, etc.) in a high-dimensional vector space. Embeddings capture semantic meaning, enabling similarity searches, recommendations, and clustering.
Vector Database
A database optimized for storing and querying high-dimensional vectors (embeddings). Vector databases power semantic search, recommendation systems, and RAG applications. Examples include Pinecone and Weaviate.
Diffusion Model
A generative AI architecture that creates images by gradually denoising random noise. Diffusion models power image generators like DALL-E, Midjourney, and Stable Diffusion.
Build on the Best AI Domain
From LLMs to AI agents — whatever you're building in AI, start with the perfect domain.
Back to