Artificial Intelligence Glossary

AGI stands for Artificial General Intelligence, which means an AI system with general, human-level (or beyond) ability to learn, reason, and apply knowledge across a wide range of tasks and domains.

Agentic AI refers to AI systems designed to act as autonomous or semi-autonomous agents: they can set or interpret goals, plan and sequence actions, use tools (like web browsers, code, or APIs), make decisions based on feedback, and adapt over time to complete tasks.

AI Alignment means making sure an AI system’s goals and behavior match what people actually want—our values, rules, and intentions.

AI Benchmarks are standardized tests used to measure and compare how well AI systems perform on specific tasks, like answering questions, recognizing images, writing code, or following instructions.

AI Safety is the field focused on ensuring AI systems behave reliably and don’t cause harm, even when they’re powerful, widely deployed, or operating in unexpected situations.

An Algorithm is a set of step-by-step instructions for solving a problem or completing a task, similar to a recipe.

Artificial Intelligence (AI) is a term coined in 1955 by John McCarthy, Stanford's first faculty member in AI, who described it as "the science and engineering of making intelligent machines."

An Attention Mechanism is a method in neural networks that helps a model focus on the most relevant parts of the input when producing an output.

Backpropagation is how neural networks learn from mistakes by working backward through the network to figure out which parts caused the error.

Bayesian Networks are graphical models that represent cause-and-effect relationships between variables using probabilities, like a map showing how different factors influence each other.

Bias in AI occurs when a system produces results that favor or discriminate against certain groups of people.

Big Data is extremely large datasets, too large to be analyzed by traditional data-processing software, that can be analyzed using AI to reveal patterns and trends.

A Chatbot is a computer program designed to simulate conversation with humans, typically through text or voice interactions.

Also called proprietary software, Closed Source refers to software whose underlying code is restricted and not available for the public to view, modify, or use.

Computer Vision is a field of AI that enables computers to see, identify, and understand visual information from images and videos, similar to how humans see and process this information.

Context Window is the is the amount of input (like text) that an AI system can process at one time during a task.

Contrastive Learning is a machine learning technique where the model learns by comparing similar and dissimilar examples to understand what makes things alike or different.

Data Augmentation is a technique to artificially expand a training dataset by creating modified versions of existing data without collecting anything new.

Data Mining is the process of discovering patterns and trends in large datasets using statistical methods and machine learning.

A Decision Tree is a machine learning algorithm that makes predictions by asking yes/no questions, splitting data at each step based on different features until reaching a final conclusion.

Deep Learning is a subset of machine learning that uses large multi-layer neural networks to automatically learn complex patterns from data.

Diffusion Models are a type of generative model that creates new content like images by adding and then subtracting “noise.”

Dimensionality Reduction is a technique for simplifying complex data by reducing the number of variables while preserving the most important information.

Embeddings are numerical representations that convert complex data (like words, images, or other objects) into vectors of numbers that capture their meaning or characteristics.

Ensemble Methods are machine learning techniques that combine multiple models (often called "weak learners") to produce a single, more accurate and robust prediction than any individual model could achieve alone.

Ethical AI is the design, development, and deployment of artificial intelligence systems that align with human values, fairness, transparency, and societal well-being.

Expert Systems are AI programs designed to mimic the decision-making abilities of human experts in specific domains by using a knowledge base of facts and a set of logical rules to draw conclusions, mainly using if-then rules.

Explainable AI (XAI) are methods and techniques that make AI systems' decisions and predictions understandable and interpretable to humans, rather than operating as opaque "black boxes."

Federated Learning is a machine learning approach where a model is trained across multiple decentralized devices or servers that hold local data, without the data ever leaving its original location.

Few-Shot Learning is a machine learning approach where models can learn to recognize or perform new tasks with only a small number of training examples.

Fine-Tuning is the process of taking a pre-trained model and further training it on task or domain specific data. I

Foundation Models are large-scale AI models, often transformers, trained on vast amounts of broad, diverse data that can be adapted to perform a wide variety of downstream tasks, serving as a "foundation" for many different applications.

Generative AI (or GenAI) refers to AI systems that can create new content like text, images, music, code, or video.

GANs (Generative Adversarial Networks) are a type of AI architecture consisting of two neural networks - a “generator” and a “discriminator” - that compete against each other in a process to create realistic synthetic data.

Generative Pre-Trained Transformer (GPT) is a family of large language models developed that uses the transformer architecture to generate human-like text based on input prompts.

GPU (Graphics Processing Unit) is a specialized electronic chip originally designed to rapidly render graphics and images by performing many mathematical calculations simultaneously in parallel.

Hallucinations in AI refers to instances where an artificial intelligence system generates information or responses that are incorrect, misleading, or entirely fabricated but presented as factual.

Human-Centered Artificial Intelligence (HAI) is an approach to AI that prioritizes human needs, values, and well-being throughout the development and deployment of AI systems.

Human-Computer Interaction (HCI) is the process through which people operate and engage with computer systems.

Human-in-the-Loop refers to AI systems that include human feedback or intervention as part of their operation.

A Hyperparameter is a parameter whose value is set before the learning process of a machine learning model begins.

In artificial intelligence, Inference is when a trained AI model makes predictions or decisions on new data it hasn't seen before.

Interpretability refers to the degree to which humans can understand how an AI system arrives at its decisions or predictions.

k-NN is a simple, intuitive machine learning algorithm used for classification and regression.

A Knowledge Graph is a structured database that represents information as a network of interconnected entities and their relationships.

A Large Language Model is an AI system trained on massive amounts of text data to understand and generate human-like language.

Latent Space is a compressed, abstract representation where high-dimensional data (like images, text, or audio) is encoded into a lower-dimensional mathematical space that captures the essential features and patterns.

Large Language Model Operations (LLMOps) is the practice of managing the entire lifecycle of LLM-based applications in production environments.

A Loss Function (also called a cost function or objective function) is a mathematical measure that quantifies how wrong a machine learning model's predictions are compared to the actual correct values.

Machine Learning is a branch of artificial intelligence that enables computers to learn patterns and make decisions from data without being explicitly programmed with rules.

A Markov Chain is a mathematical model that describes a sequence of events where the probability of each future event depends only on the current state, not on the history of how you got there.

Machine Learning Operations (MLOps) is a set of practices that combines machine learning, software engineering, and DevOps to deploy, monitor, and maintain ML models reliably in production environments.

A Model is a simplified mathematical or computational representation of a real-world system, process, or relationship that is used to make predictions or understand patterns.

Model Drift occurs when a machine learning model's performance degrades over time because the real-world data it encounters has changed from the data it was originally trained on.

Multimodal AI refers to artificial intelligence systems that can process, understand, and generate multiple types of data modalities simultaneously—such as text, images, audio, and video.

Natural Language Processing (NLP) is a branch of artificial intelligence focused on enabling computers to understand, interpret, and generate human language in a meaningful way.

A Neural Network is a computational model inspired by the structure of the human brain, consisting of interconnected layers of artificial "neurons" that process and transmit information.

An Optimization Algorithm is a method that helps a machine learning model get better by adjusting its settings to make fewer mistakes.

Overfitting happens when a model memorizes the training data too closely, including mistakes and random patterns.

An Open-Weight Model is an AI model whose core components are publicly released, allowing anyone to download it.

Open Source refers to software where its original design, or "blueprint," is made freely available for anyone to see and use.

A Parameter is an internal variable within a machine learning model that is learned and adjusted during the training phase.

Predictive Analytics is the practice of using data, statistical methods, and machine learning models to forecast future outcomes or trends.

Prompt Engineering is the practice of carefully crafting instructions, or "prompts," to guide AI language models toward producing desired outputs.

Prompt Injection is a type of security attack that uses malicious input to trick a Large Language Model (LLM) into behaving in an unintended way.

Retrieval-Augmented Generation (RAG) is a technique that helps language models generate higher-quality outputs by allowing them to look up external, up-to-date information first.

A Reasoning Model is a type of AI system designed to solve complex problems by generating a logical, step-by-step sequence of thought.

Reinforcement Learning is a type of machine learning where an AI agent improves its performance through trial and error by taking actions within a specific setting.

Responsible AI refers to the frameworks, principles, and practices that guide the ethical and safe development and deployment of artificial intelligence systems.

Robotics is the field that combines engineering and computer science, and now often artificial intelligence, to design and build machines capable of performing physical tasks.

Spatial Intelligence is the ability to understand and reason about the three-dimensional physical world, including how objects relate to each other in space, how they move, and how they interact.

Self-Supervised Learning is a training method where an AI model teaches itself by creating its own puzzles from raw data and then trying to solve them.

Semantic Analysis is the process of understanding the meaning of language by examining the relationship between words, phrases, and symbols.

Scaling Laws are predictable mathematical relationships that describe how AI model performance improves as factors like model size, training data, and computing power increase.

Supervised Learning is a machine learning approach where models are trained on labeled data—input examples paired with correct output answers.

Synthetic Data is artificially generated information created by algorithms or simulations rather than collected from real-world events or observations.

A Tensor is essentially a container for numbers organized in multiple dimensions, like a more advanced version of a spreadsheet.

Tokenization is the process of breaking down text into smaller units called tokens—which can be words, parts of words, or even individual characters—that AI language models can process.

Traditional AI refers to earlier approaches to artificial intelligence that relied on explicitly programmed rules, logic, and human-defined knowledge rather than learning from data.

Training Data is the collection of examples—such as text, images, audio, or other information—used to teach machine learning models how to perform specific tasks.

Transfer Learning is a machine learning technique where a model trained on one task is reused as the starting point for a different but related task.

A Transformer is a neural network architecture that revolutionized AI by using a mechanism called "attention" to process and understand relationships between all parts of input data simultaneously, rather than sequentially.

The Turing Test, proposed by mathematician Alan Turing in 1950, is a measure of a machine's ability to exhibit intelligent behavior indistinguishable from a human.

Unsupervised Learning is a machine learning approach where models are trained on data without labeled answers or predefined categories, tasked with finding patterns and structure on their own.

A Vector Database is a specialized type of database designed to store and efficiently search through high-dimensional numerical representations (vectors) of data like text, images, or audio.

A Vision Transformer (ViT) is an adaptation of the transformer architecture, originally designed for language, to process and analyze images.

Weights are the numerical parameters within a neural network that determine the strength of connections between artificial neurons and ultimately shape how the model processes information.

Zero-Shot Learning is the ability of an AI model to perform tasks or recognize categories it has never been explicitly trained on, using only its general knowledge and understanding.