200+ AI Terms Explained: The Complete AI Glossary for Beginners (2026 Edition)

Artificial intelligence (AI) is filled with specialized terminology and jargon that can be overwhelming for beginners.

As you start exploring the world of AI, you’ll inevitably encounter novel concepts and unfamiliar words used to describe them. However, grasping the core vocabulary is critical to unlocking a deeper understanding of AI.

That’s why we created this AI glossary, covering common AI terms from A to Z. Understanding these foundational terms will equip you to better comprehend AI literature, research, and discussions.

With clear explanations of key concepts, this glossary aims to make the specialized vocabulary of AI more accessible. Whether you’re a student, developer, or simply AI-curious, this reference will help you navigate the complex lexicon of artificial intelligence. Let’s embark on this enlightening journey together.

Latest Update: Dec 29, 2025

A

• Activation Function: Math functions like sigmoid, ReLU applied to neurons to introduce non-linearity into neural networks.
• Adversarial Attack: Carefully constructed inputs meant to fool AI systems by exploiting vulnerabilities.
• Adversarial Robustness: The ability of AI systems to withstand adversarial attacks.
• Agent: An autonomous entity that can perceive and act upon an environment.
• Agent2Agent Protocol (A2A): An open protocol that complements Anthropic’s Model Context Protocol (MCP), which provides helpful tools and context to agents.
• Agentic AI / AI Agent Systems: AI systems, often powered by LLMs, designed to autonomously perform tasks, make decisions, and interact with digital environments or tools to achieve specific goals. They can plan, execute multi-step operations, and learn from feedback.
• AI Inference: The phase where a trained model generates outputs from new inputs, as opposed to training.
• Agent Orchestration: The process of coordinating multiple AI agents, tools, and workflows so they can collaborate toward a shared goal.
• AGI (Artificial General Intelligence): A hypothetical type of artificial intelligence that would have the ability to understand and reason about the world in a way that is indistinguishable from a human.
• AI Ethics: Examining the ethical impact of AI systems and developing them responsibly.
• AI Alignment: A subfield of AI safety that aims to ensure that artificial intelligence systems achieve desired outcomes.
• AIGC (AI Generated Content): Any form of content that is created by artificial intelligence rather than human beings.
• Algorithm: A set of rules or steps that a computer follows to complete a task.
• Alignment Tax: The trade-off between model capability and safety constraints introduced during alignment and fine-tuning.
• AlphaGo: Game-playing AI system by DeepMind that defeated world champion in Go.
• ANI (Artificial Narrow Intelligence): AI systems that are designed and trained to perform a specific task without possessing the general problem-solving abilities that a human has. Unlike Artificial General Intelligence (AGI), which would have the capability to understand, learn, and apply knowledge in different domains, ANI focuses on a narrow, well-defined task.
• Artificial intelligence: The field of computer science that deals with the creation of intelligent agents. AI research has been highly successful in developing effective techniques for solving a wide range of problems.
• Artificial Neural Network (ANN): A computing system inspired by the human brain’s neural networks, used for processing complex patterns of information.
• ASI (Artificial Superintelligence): A theoretical form of AI that surpasses human intelligence across all domains, including creativity, general wisdom, problem-solving, and emotional intelligence.
• Attention Layers: Part of a neural network that helps the model focus on relevant features of the input data by weighting the significance of different parts of the data.
• Attention Mechanism: A component of neural networks that allows them to focus on specific parts of the input.
• Autoencoder: A type of neural network used for unsupervised learning and dimensionality reduction.
• Autonomous: Operating without human intervention.
• Azure Machine Learning: A cloud-based service by Microsoft for building, training, and deploying machine learning models.

B

• Backpropagation: Algorithm used to calculate loss and adjust weights in neural networks.
• Batch Normalization: Normalizing activations throughout a neural network to stabilize training.
• Bayesian Networks: Probabilistic model representing variables and conditional dependencies via graph.
• BERT (Bidirectional Encoder Representations from Transformers): A method from Google for pre-training language representations.
• Bias: Systematic error introduced by flawed assumptions in data or algorithms.
• Big Data: Extremely large data sets analyzed computationally to reveal patterns.

C

• Capsule Networks: An alternative to CNNs using capsules to represent parts of objects.
• Chatbot: A software application designed to simulate human conversation.
• ChatGPT: A conversational AI model by OpenAI.
• Classification: Categorizing input data among a set of target classes or categories.
• Claude: A next-generation AI assistant.
• Cloud AutoML: Google Cloud’s suite of machine learning products that enables developers with limited expertise to train high-quality models.
• Clustering: Groupings inputs based on similarity, used in unsupervised learning.
• CNN (Convolutional Neural Network): A type of deep learning neural network that is particularly well-suited for image recognition and classification tasks.
• Cognitive Computing: Enabling systems to learn, reason, and engage with humans naturally.
• Compute Budget: A constraint on how much computational resource (time, tokens, FLOPs) a model or agent can use per task.
• Computer Vision: Algorithms for processing, analyzing and understanding visual data.
• Connectionism: A framework for understanding intelligence as the emergent property of interconnected networks of simple processing units.
• Context Caching: A technique to reduce costs and latency by storing and reusing previously processed input tokens (like long documents or codebases), so the model doesn’t need to re-read them for every new prompt.
• Context Engineering: The practice of structuring prompts, memory, tools, and retrieved data to guide an AI system’s behavior more reliably.
• Context Window: The maximum amount of text or data that a language model can process at once, determining how much information it can consider when generating responses.
• Convolutional Neural Network (CNN): Neural nets using convolutional layers for tasks like image classification.
• Copilot: GitHub’s AI pair programmer to suggest code in real time.
• CoT (Chain-of-thought): A technique for guiding large language models (LLMs) to generate reasoning steps when answering a question or completing a task.
• Cross-modal Generalization: The ability to apply knowledge learned in one sensory modality to another modality.
• CV (Computer Vision): Extract useful information from images and videos, such as identifying objects and people, tracking their movement, and understanding their interactions with the environment.

D

• Data Augmentation: Artificially increase the size of a training dataset by creating modified versions of existing data.
• Data Leakage: When information leaks from test data to training data, causing overfitting.
• Data Mining: Extracting insights from large data sets to uncover patterns.
• DALL·E: An OpenAI model that generates images from textual descriptions.
• Deep Learning: Neural networks with many layers that can extract high-level features from raw data.
• DeepMind: A British AI company, subsidiary of Alphabet Inc., known for breakthroughs in deep learning and AI for games.
• Decision Tree: A flowchart-like structure in which each internal node represents a test on an attribute, each branch represents the outcome of the test, and each leaf node represents a class label.
• Deliberate Reasoning: A reasoning approach where models spend additional computation time to evaluate intermediate steps before producing a final answer.
• Diffusion Models: A type of generative model that can be used to generate realistic images, text, and other types of data.
• Diffusion Transformer (DiT): A hybrid architecture that combines diffusion models with transformer-based structures, commonly used in image and video generation.
• Dimensionality Reduction: Reducing number of variables considered, simplifying data.
• Distributed Computing: Splitting computations across multiple processors to parallelize workload.
• Double Descent: A phenomenon in machine learning where increasing the number of model parameters first leads to a decrease in performance, and then to an increase in performance.

E

• Echo State Networks: A type of recurrent neural network with a sparsely connected hidden layer, primarily used for time-series prediction where traditional training methods are impractical.
• Edge AI: Running AI models directly on local devices instead of cloud servers to reduce latency and improve privacy.
• Embedding: A technique for representing high-dimensional data as vectors in a lower-dimensional space.
• Embedding Model: A specialized model used only to convert text, images, or other data into vector representations.
• End-to-end learning: A machine learning approach where a single model is trained to perform a task from input to output without any intermediate steps.
• Ensemble Models: Combining multiple models to produce predictions that are more robust.
• Epoch: One cycle through the full training dataset in machine learning.
• Evolutionary Algorithm: Algorithms that use mechanisms inspired by biological evolution, such as reproduction, mutation, and selection.
• Expert system: A computer system that emulates the decision-making abilities of a human expert. Expert systems are used in a variety of applications, such as medical diagnosis, financial planning, and legal reasoning.
• Explainable AI (XAI): Making opaque AI systems interpretable by humans.

F

• Facial Recognition: Identifying or verifying individuals by analyzing facial characteristics.
• False Positive: Incorrect classification of an input as positive for the condition being tested.
• Feature Engineering: Transforming raw data into features that better represent patterns.
• Federated Learning: Training algorithm distributed across decentralized edge devices.
• Few-shot Learning: A machine learning approach that enables models to learn new tasks from a very small number of examples.
• Fine-tuning: Taking a pre-trained model and retraining it on a new dataset.
• Fitting: The process of training a machine learning model on a dataset.
• Forward Propagation: Calculating the output of a neural network
• Foundation Model: A large language model (LLM) that has been trained on a massive dataset of text and code.
• Function Calling: The capability of Large Language Models (LLMs) to identify when a query or task requires external tools, data, or APIs to be completed. The LLM can then formulate a “call” to that tool (e.g., a weather API, a calculator, a database search) and integrate the tool’s output back into its response.
• Function Schema: A structured definition that describes how an AI model should call external tools or APIs.
• Fuzzy Logic: A computing approach based on “degrees of truth” rather than the usual true or false binary logic.

G

• GAN (Generative Adversarial Network): Neural networks that are trained to produce new data that mimics some existing data.
• Gemini: A series of multimodal models developed by Google DeepMind, designed to understand, operate across, and combine various types of information like text, code, images, audio, and video.
• Generalization Ability: The ability of a model to perform well on new data that it has never seen before.
• Generative AI: Artificial intelligence capable of generating text, images, or other media, using generative models. 
• Genetic Algorithm: A search heuristic inspired by the process of natural selection.
• Google Brain: Google’s deep learning artificial intelligence research team.
• GPT (Generative Pre-trained Transformer): A series of language representation models by OpenAI.
• Gradient Boosting: Successively training weak learners to improve predictive performance.
• Gradient Descent: An optimization algorithm commonly used to train machine learning models. It works by iteratively adjusting the parameters of the model in the direction of the negative gradient of the loss function.
• Graphical Model: A type of probabilistic model that uses a graph to represent and map out dependencies.
• GraphRAG: An evolution of RAG that uses Knowledge Graphs to structure retrieved information. It helps the AI understand the “big picture” and relationships between concepts, not just keyword matching.
• Grok: A conversational AI model developed by xAI, designed to answer questions with a bit of wit and a rebellious streak, and with real-time access to information via the X platform.
• Groq (LPU): A hardware company that produces LPUs (Language Processing Units), chips designed specifically to run LLMs at incredibly high speeds (hundreds of tokens per second).
• Grounding: The process of tying model outputs to verified data sources or real-world references.

H

• Hallucinate: Describing when an AI model generates incorrect information, but presents it as if it were a fact.
• Hardware: Physical computer machinery needed to run machine learning algorithms.
• Heuristic: An approach to problem solving relying on practical methods and experience.
• Hidden Layer: A layer of neurons that is located between the input layer and the output layer.
• Hugging Face: A company known for its Transformers library, which provides state-of-the-art general-purpose architectures for natural language understanding and generation.
• Human-in-the-Loop (HITL): A system design where humans review, correct, or guide AI outputs during training or deployment.
• Hypernetworks: A type of neural network architecture where one neural network generates the weights for another network, enabling dynamic adjustments of network architecture and functionality.
• Hyperparameter Tuning: Optimizing hyperparameters to improve model performance on data.
• Hypothesis: An initial assumption made about the data.

I

• IBM Watson: A suite of AI tools and applications by IBM.
• ImageNet: A large-scale dataset used for visual object recognition software research.
• Image Recognition: Identifying objects or features within images or videos.
• Incremental Learning: A method where the learning model is capable of learning continuously, adapting to new data without forgetting its previously learned knowledge.
• Inference: Applying a trained machine learning model to make predictions on new data.
• Inference-Time Scaling: Improving model performance by increasing computation during inference rather than increasing model size.
• Information Retrieval: The process of obtaining information from a database using a query.
• Instance: A single data point or example in a dataset.
• Instruction Tuning: A technique for fine-tuning large language models (LLMs) to follow instructions more accurately and comprehensively.
• Interpretability: Ability to explain why AI systems behave in certain ways.

J

• Julia: A high-level, high-performance programming language for technical computing, with syntax familiar to users of other technical computing environments.
• Jupyter Notebook: An open-source web application for interactive computing and data visualization.
• Joint Probability: The probability of two events happening at the same time.
• JSON (JavaScript Object Notation): A lightweight data-interchange format that’s easy for humans to read and write.

K

• K-means Clustering: Unsupervised algorithm grouping data points into k clusters based on similarity.
• Kernel: A function used in the machine learning algorithm to map a lower-dimensional data into a higher-dimensional data.
• KNN (K-Nearest Neighbors): A simple, instance-based learning algorithm.
• Knowledge Distillation: Transferring the knowledge from a large, complex teacher model to a smaller, simpler student model.
• Knowledge Graph: Database of real-world entities and relationships between them.
• Knowledge Representation: The field of AI dedicated to representing information about the world in a form that a computer system can utilize to solve complex tasks such as diagnosing a medical condition or having a dialogue in natural language.
• KV Cache (Key-Value Cache): A memory optimization technique used in transformer inference to reuse previous attention computations.

L

• LaMDA: Google’s conversational AI system meant to be indistinguishable from humans.
• Latency: The time delay between an input request and the model’s response.
• Latent Variable: A variable that’s not directly observed but inferred from other variables.
• Lazy Learning: Algorithms that defer processing until needed, storing training data instead.
• Learning Rate: Determines the step size at each iteration while moving towards a minimum of the loss function.
• Lifelong Learning: The ability of an AI system to continuously learn and incorporate new knowledge over time, without forgetting or catastrophically interfering with previously learned skills and information.
• Llama: An open-source large language model (LLM) from Meta.
• LLM (Large Language Model): A type of machine learning model that is trained on a massive dataset of text and code. This allows the model to learn the statistical relationships between words and phrases, and to generate text that is both grammatically correct and semantically meaningful. While originally text-based, modern LLMs (like GPT-5, Claude 4.5, Gemini 3) are increasingly multimodal, capable of natively understanding and generating code, images, and audio.
• Logistic Regression: Predictive modeling method suited for binary classification tasks.
• Long-Context Model: A language model designed to process very large context windows, often exceeding hundreds of thousands of tokens.
• LoRA (Low-Rank Adaptation): An efficient fine-tuning technique for large pre-trained models. It works by freezing the original model weights and injecting trainable, low-rank matrices into specific layers (e.g., attention layers of Transformers), significantly reducing the number of trainable parameters and computational cost for adaptation.
• Loss Function: A mathematical function that quantifies the difference between the predicted and actual values in a machine learning model.
• LSTM (Long short-term memory: A type of recurrent neural network (RNN) that is specifically designed to handle sequential data

M

• Machine Learning: Algorithms that can learn from data to make predictions or decisions.
• Machine Translation: Automated translation of text or speech from one language to another.
• Magenta: Google AI project to generate art and music using ML.
• Maximum entropy: A principle of machine learning that states that the best model is the one that makes the fewest assumptions about the data. Maximum entropy models are often used in natural language processing and computer vision.
• Markov Chain: A sequence of events in which the probability of each event depends only on the state attained in the previous event.
• Matrix Factorization: Decomposing a matrix into factors to discover latent features.
• MCP (Model Context Protocol): A standardized protocol for connecting AI models with external data sources and tools, enabling more seamless integration and context sharing across different AI applications.
• Meta-learning: The idea that AI systems can learn how to learn.
• Midjourney: A generative artificial intelligence program and service created and hosted by San Francisco-based independent research lab Midjourney, Inc. 
• Mixtral: A family of sparse Mixture of Experts (SMoE) large language models, such as Mixtral 8x7B, known for their strong performance and efficiency, often outperforming larger dense models by selectively activating only a fraction of their parameters (“experts”) for any given input.
• Mixture of Agents (MoA): An architecture where multiple AI agents with different specializations collaborate to solve complex problems, each contributing their expertise to the overall solution.
• Mixture of Experts: Combining the predictions of multiple expert models, each of which is specialized in a specific portion of the data.
• Model: A representation of a system to help understand and predict the system’s behavior.
• Model Collapse: A degenerative process where AI models trained on AI-generated data (synthetic data) eventually lose quality, diversity, and grasp of reality.
• Model Routing: Dynamically selecting which model or expert should handle a specific task or input.
• Multimodal Chain-of-Thought: Extending chain-of-thought reasoning to work across multiple data modalities (text, images, audio), enabling more comprehensive problem-solving approaches.
• Multimodal LLM: A Large Language Model that can process and generate information from multiple types of data (modalities) simultaneously, such as text, images, audio, and video. It can understand relationships and context across these different data types.
• Multimodal Tokenization: The process of converting text, images, audio, or video into a unified token format.

N

• Natural Language Processing (NLP): Automating the analysis and generation of natural human language.
• NeRF: Creating photorealistic 3D models of objects and scenes from 2D images.
• Neural Architecture Search: Automating the design of neural network architectures.
• Neural Networks: Algorithms modeled loosely on the human brain’s neurons.
• Neuroevolution: A form of artificial intelligence that uses evolutionary algorithms to generate artificial neural networks, parameters, topology, and rules.

O

• Occam’s Razor: The problem solving principle that the simplest solution tends to be the best.
• Optimization: Iteratively tuning parameters to minimize error and improve model performance.
• Orchestrator Agent: A supervisory agent responsible for task delegation, monitoring, and coordination among other agents.
• Outlier: A data point that’s significantly different from other data points.
• Overfitting: When a model fits the training data too closely but generalizes poorly.
• Ontology: A set of concepts and categories in a subject area that shows their properties and the relations between them.

P

• Perception: The process of acquiring information about the environment. Perception is a key component of many AI applications, such as robotics, computer vision, and speech recognition.
• Perceptron: Early and simple neural network model for binary classification tasks.
• Planning: The process of generating a sequence of actions to achieve a goal. Planning algorithms are used in a variety of AI applications, such as robotics, scheduling, and decision making.
• Planning Module: A component in agent systems that decomposes goals into ordered steps.
• Post-training Alignment: Fine-tuning methods applied after pretraining to shape behavior, safety, and instruction-following.
• Precision: Fraction of results returned by a model that are relevant.
• Predictive Modeling: Using statistics to predict outcomes.
• Principal Component Analysis (PCA): A method used to emphasize variation and bring out strong patterns in a dataset.
• Probabilistic Modeling: Representing uncertainty and randomness to model real world data.
• Prompt: In AI, a prompt is a piece of text that provides instructions or guidance to an AI model. It can be used to tell the model what task to perform, what kind of output to generate, or what style or tone to use.
• Prompt Engineering: The process of designing and refining prompts—questions or instructions—to elicit specific responses from AI models.
• PyTorch: An open-source machine learning framework developed by Facebook.

Q

• Q-Learning: Reinforcement learning technique using a reward system.
• Quantization: Reducing numerical precision of model weights to improve inference speed and reduce memory usage.
• Quantum Computing: Computing using quantum bits or qubits.
• Query: A request for data or information from a database.

R

• RAG (Retrieval-Augmented Generation): An AI framework that enhances the capabilities of Large Language Models (LLMs) by connecting them to external, up-to-date knowledge sources. When prompted, a RAG system first retrieves relevant information from a specified database or document collection and then provides this information as context to the LLM, which uses it to generate a more accurate, detailed, and factually grounded response.
• Random Forest: Ensemble method combining predictions from many decision trees.
• Reasoning Models: AI systems specifically designed to perform complex logical reasoning, mathematical problem-solving, and multi-step analysis rather than just pattern matching or generation.
• Reasoning Trace: An explicit or implicit record of intermediate steps used by a model to reach a conclusion.
• Recall: Fraction of total relevant results correctly classified by algorithm.
• Recommender Systems: Predicting user preferences for products or content.
• Recurrent Neural Network (RNN): Neural networks with loops, allowing information to persist.
• Reflection: A technique where an AI system reviews and critiques its own output to improve future responses.
• Regression: Statistical models estimating relationships between variables.
• Reinforcement Learning from Human Feedback (RLHF): A training method that uses human preferences to fine-tune AI models, helping align their outputs with human values and expectations.
• Recurrent Neural Networks (RNN): A class of neural networks where connections between nodes form a directed graph along a temporal sequence, allowing it to exhibit temporal dynamic behavior.
• Robotics: The field of engineering that deals with the design, construction, operation, and application of robots. Robots are machines that can be programmed to perform tasks. AI is used to control robots and give them autonomy.
• Rule-based system: A computer system that uses a set of rules to make decisions. Rule-based systems are often used in expert systems and decision support systems.

S

• Self-attention: A mechanism within neural networks that allows them to weigh the importance of different inputs independently, useful particularly in transformer models for tasks like language understanding and translation.
• Self-Supervised Learning: Using unlabeled data to pretrain models.
• Semantic Segmentation: A process in computer vision that involves dividing an image into parts and classifying each part at the pixel level, helping the model understand and label whole scenes in detail.
• Semi-supervised Learning: Using both labeled and unlabeled data for training.
• Sentiment Analysis: Determining emotional tone behind text data.
• Sequence Model: Algorithms like RNNs and LSTMs for ordered data like text or time series.
• Siamese Networks: Neural nets that compare two inputs.
• Singular Value Decomposition (SVD): Matrix factorization method for reducing dimensionality.
• SLM (Small Language Model): Compact AI models (e.g., Microsoft Phi, Google Gemma, Meta Llama 8B) designed to run efficiently on local devices like laptops or phones without needing cloud connection. 
• Sovereign AI: The strategic initiative by nations to build and own their own AI infrastructure, data, and models to ensure digital independence and national security, rather than relying on foreign tech giants.
• Sora: A text-to-video generative AI model developed by OpenAI, capable of creating realistic and imaginative video scenes up to a minute long from textual prompts, demonstrating advanced understanding of physical world dynamics and object interactions.
• Spatial Transformer Networks: A neural network module that explicitly allows the spatial manipulation of data within the network, enabling it to actively spatially transform feature maps according to the learned task.
• Speculative Decoding: An inference optimization method where smaller models predict tokens ahead to accelerate generation.
• Spike Neural Networks: Networks that incorporate the timing of neuron spike events, making them efficient for processing temporal data.
• Supervised Learning: Creating models from labeled training data.
• Support vector machine (SVM): A type of machine learning model that is used for classification and regression. SVMs work by finding a hyperplane that separates the data points into different classes.
• Swarm Intelligence (AI Agents): Multiple agents operating collectively with decentralized decision-making.
• Synthetic Data: Artificially generated training data.
• System Prompt: Instructions given to AI models that define their role, behavior, and constraints, serving as persistent context that guides how they respond to user queries.

T

• Tensor: A mathematical object analogous to but more general than a vector.
• TensorFlow: End-to-end open source platform for machine learning.
• Test-Time Compute: Additional computation allocated during inference to improve reasoning accuracy.
• Tool-Augmented LLM: A language model that can actively call external tools, APIs, or databases.
• Transfer Learning: Applying knowledge gained in one domain to a related domain.
• Transformer: Attention-based neural network architecture.
• Tree-Based Models: Algorithms like random forests and gradient boosting using decision trees.
• Triplet Loss: A loss function used in machine learning to learn embeddings or transformations by comparing a base input to a positive input (similar) and a negative input (differing) to ensure that similar items are closer in the embedding space than differing items.

U

• Unsupervised Learning: Finding patterns in unlabeled, unclassified data.
• Underfitting: When a machine learning model is too simple and doesn’t capture the underlying trend of the data.
• Utility Theory: A decision-making approach based on the assumption that decisions are made to maximize pleasure and minimize pain.

V

• Validation Set: Data used to tune hyperparameters and evaluate models while training.
• Variable selection: The process of selecting a subset of features from a larger set of features. Variable selection is used to improve the performance of machine learning models by reducing the number of features that the model needs to learn.
• Vector: A quantity having direction as well as magnitude.
• Vibe Coding: A coding trend in 2025 where developers focus on describing the high-level “vibe” or intent of an application to an AI, letting the AI handle the implementation details.
• Video Understanding Model: A model designed to interpret actions, events, and temporal relationships in video data.
• Vision-Language Models (VLMs): AI systems that can understand and generate content involving both visual and textual information, enabling tasks like image captioning, visual question answering, and multimodal reasoning.
• Vision Recognition: The ability of software to identify objects, places, people, writing, and actions in images.

W

• Weight Initialization: Strategies for initializing weights in neural networks prior to training.
• Weights: Values in a neural network that are adjusted during training.
• Word Embedding: The representation of words in dense vectors of real numbers.

X

• XAI (Explainable AI): Making AI decisions understandable to humans.
• XGBoost: Scalable, optimized implementation of gradient boosting algorithm.

Y

• YOLO (you only look once): A type of object detection algorithm that uses a single neural network to detect objects in an image. YOLO algorithms are fast and accurate, making them well-suited for real-time applications such as self-driving cars and robotics.

Z

• Zero-shot learning: A type of machine learning that involves training a model to recognize new classes that it has never seen before. Zero-shot learning is a challenging problem, but it has the potential to enable AI systems to learn new information quickly and easily.

2025–2026 Update

Artificial intelligence has evolved rapidly over the past two years. Large language models are no longer used in isolation. They now operate as parts of larger systems that involve agents, tools, memory, retrieval, reasoning, and multimodal inputs.

As a result, modern AI literacy requires more than understanding models and algorithms. It requires familiarity with inference workflows, agent coordination, reasoning strategies, and efficiency constraints. This updated glossary reflects those shifts by introducing terminology that describes how AI systems are built, deployed, and controlled in real-world applications today.

Final Thoughts

AI terminology will continue to expand as models become more capable and systems become more complex. This glossary is designed to give beginners a durable foundation, not just a snapshot of the moment.

We will continue updating this reference as new concepts emerge. If you encounter AI terms that feel unclear or underexplained, they likely belong in the next revision.