AI Glossary
Every concept you need to navigate the world of Artificial Intelligence — from core fundamentals to cutting-edge research. Clear definitions, real-world context, expert-level depth.
Fundamentals
5 termsArtificial Intelligence (AI)
The capability of computer systems to perform tasks typically associated with human intelligence — including learning, reasoning, perception…
Narrow AI (Weak AI)
The only form of AI that currently exists. Systems designed and trained for a specific, limited task — such as playing chess, recognizing fa…
Artificial General Intelligence (AGI)
A theoretical form of AI with human-level cognitive flexibility — capable of understanding, learning, and solving any intellectual task that…
Artificial Superintelligence (ASI)
A hypothetical level of intelligence that would surpass human cognitive capabilities in virtually all domains — from scientific creativity t…
Turing Test
A test proposed by Alan Turing in 1950 to evaluate whether a machine can exhibit intelligent behavior indistinguishable from a human in natu…
Machine Learning
18 termsMachine Learning (ML)
A subfield of AI that develops algorithms allowing machines to learn patterns from data and make predictions or decisions — without being ex…
Data Science
An interdisciplinary field combining statistics, programming, and domain expertise to extract knowledge and actionable insights from structu…
Supervised Learning
A Machine Learning paradigm where a model is trained on a labeled dataset — examples with known correct answers — so it can learn to make pr…
Unsupervised Learning
A Machine Learning paradigm that works with unlabeled data, discovering hidden patterns, structures, or groupings on its own — without prede…
Reinforcement Learning (RL)
A Machine Learning paradigm where an agent learns to make decisions by interacting with an environment, receiving rewards for good actions a…
Semi-supervised Learning
A learning paradigm that combines a small amount of labeled data with a large amount of unlabeled data during training, achieving better per…
Overfitting
A modeling failure where a machine learning model learns the training data too closely — memorizing noise and edge cases — and subsequently…
Cross-Validation
A model evaluation technique that divides data into multiple subsets, repeatedly training on some and testing on the remainder, to obtain a…
Feature Engineering
The process of selecting, transforming, or creating input variables (features) from raw data to make machine learning algorithms work more e…
Hyperparameter Tuning
The process of systematically optimizing the configuration settings of a machine learning algorithm — settings set before training, not lear…
Transfer Learning
A technique where a model trained on one task is reused as the starting point for a different but related task — dramatically reducing the d…
Classification
A supervised learning task where the model learns to assign input data to one of several predefined categories or classes — such as spam vs.…
Regression
A supervised learning task where the model predicts a continuous numerical value — such as house prices, temperature, or stock returns — rat…
Clustering
An unsupervised learning technique that groups data points into clusters based on similarity — without any predefined labels — so that point…
Decision Tree & Random Forest
Decision Trees are models that make predictions by learning a hierarchy of if-then rules from data. Random Forests improve on this by combin…
Ensemble Methods
Techniques that combine multiple individual models to produce a single, more accurate and robust prediction — leveraging the principle that…
Dimensionality Reduction
Techniques that reduce the number of input features in a dataset while preserving as much meaningful information as possible — making data e…
Regularization
A family of techniques that constrain or penalize model complexity during training to prevent overfitting — ensuring the model generalizes w…
Deep Learning
16 termsDeep Learning (DL)
A subfield of Machine Learning that uses artificial neural networks with many layers to learn extremely complex patterns directly from raw d…
Artificial Neural Network (ANN)
A computational model inspired by the human brain, composed of interconnected layers of nodes (neurons) that process information and learn c…
Activation Function
A mathematical function applied to each neuron's output that introduces non-linearity, enabling neural networks to learn complex, non-linear…
Backpropagation
The foundational algorithm for training neural networks — it efficiently computes the gradient of the loss function with respect to every we…
Gradient Descent
An iterative optimization algorithm that minimizes a loss function by updating model parameters in small steps in the direction opposite to…
Convolutional Neural Network (CNN)
A neural network architecture specialized for grid-structured data (especially images) that uses learned filters to detect local features —…
Recurrent Neural Network (RNN)
A neural network architecture designed for sequential data that maintains a hidden state — a form of memory — allowing it to incorporate con…
LSTM / GRU
Advanced Recurrent Neural Network variants that use gating mechanisms to selectively retain or forget information — overcoming the vanishing…
Transformer
A neural network architecture that processes entire sequences in parallel using self-attention mechanisms — eliminating recurrence and enabl…
Attention Mechanism
A technique that allows neural networks to dynamically focus on the most relevant parts of an input when producing each element of the outpu…
Dropout
A regularization technique that randomly deactivates a fraction of neurons during each training step, forcing the network to learn more robu…
Embedding
A dense, low-dimensional vector representation of discrete data — such as words, sentences, images, or users — where semantic similarity is…
Tensor
The fundamental data structure of deep learning — a multidimensional array of numbers that generalizes scalars, vectors, and matrices to arb…
Batch Normalization
A technique that normalizes the inputs to each layer of a neural network within a mini-batch — stabilizing training, enabling higher learnin…
Encoder-Decoder Architecture
A neural network design pattern consisting of two components: an encoder that compresses input into a compact internal representation, and a…
GPU & TPU
Specialized processors that accelerate deep learning computations. GPUs (Graphics Processing Units) perform massive parallel matrix operatio…
Generative AI
20 termsGenerative AI
A branch of AI focused on models that generate new, original content — text, images, audio, code, video — that is statistically similar to t…
Large Language Model (LLM)
A Transformer-based deep learning model trained on massive text corpora — capable of understanding, generating, translating, summarizing, an…
Generative Adversarial Network (GAN)
A generative model architecture composed of two competing neural networks — a generator that creates synthetic data and a discriminator that…
Variational Autoencoder (VAE)
A generative model that learns to encode data into a structured, continuous latent space and decode it back — enabling generation of new, si…
ChatGPT
A conversational AI assistant developed by OpenAI, built on the GPT family of large language models and aligned with human preferences throu…
GPT (Generative Pre-trained Transformer)
A family of large language models developed by OpenAI using the Transformer decoder architecture, pre-trained on massive text datasets to pr…
BERT
Bidirectional Encoder Representations from Transformers — Google's landmark language model that reads text bidirectionally, capturing richer…
Fine-tuning
The process of adapting a large pre-trained model to a specific task or domain by continuing its training on a smaller, task-specific datase…
Prompt Engineering
The practice of designing, refining, and structuring inputs (prompts) given to AI language models to elicit the most accurate, relevant, and…
Diffusion Model
A generative model that creates data by learning to reverse a gradual noising process — starting from pure random noise and iteratively refi…
Hallucination
When an AI model generates output that sounds confident and plausible but is factually incorrect, fabricated, or unsupported by its training…
Tokenization
The process of breaking text into smaller units called tokens — words, subwords, or characters — that serve as the fundamental input units f…
Temperature
A parameter that controls the randomness and creativity of a language model's output — low temperature produces focused, deterministic respo…
Retrieval-Augmented Generation (RAG)
A technique that enhances language model outputs by first retrieving relevant information from external knowledge sources, then using that r…
Multimodal AI
AI systems capable of understanding, processing, and generating content across multiple data types — text, images, audio, video, and code —…
RLHF
Reinforcement Learning from Human Feedback — a training technique that aligns language models with human preferences by using human judgment…
Context Window
The maximum amount of text (measured in tokens) that a language model can process in a single input-output interaction — determining how muc…
Zero-Shot & Few-Shot Learning
The ability of AI models to perform tasks they were not explicitly trained on. Zero-shot requires no examples; few-shot uses a small number…
AI Agent
An AI system that goes beyond simple question-answering by autonomously planning, using tools, executing multi-step tasks, and making decisi…
Chain-of-Thought Prompting
A prompting technique that instructs a language model to break down its reasoning into explicit, step-by-step intermediate steps before arri…
Applications
11 termsComputer Vision
A field of AI that enables machines to interpret and understand visual information from images and video — detecting objects, recognizing fa…
Natural Language Processing (NLP)
A field of AI dedicated to enabling computers to understand, interpret, generate, and reason about human language — in text and speech form…
Object Detection
A computer vision task that identifies and locates multiple objects within an image or video, typically outputting both a class label and a…
Semantic Segmentation
A computer vision task that classifies every pixel of an image into a semantic category, producing a dense map that labels each pixel as bel…
Sentiment Analysis
An NLP technique that automatically determines the emotional tone or opinion expressed in text — typically classifying it as positive, negat…
Named Entity Recognition (NER)
An NLP task that identifies and classifies named entities in text — such as people, organizations, locations, dates, and monetary values — e…
Speech Recognition
The AI capability that converts spoken language into written text — enabling voice assistants, transcription services, and hands-free interf…
Recommender System
An AI system that predicts and suggests items — products, content, music, connections — a user is likely to be interested in, based on patte…
Anomaly Detection
The identification of data points, events, or patterns that deviate significantly from expected behavior — used to detect fraud, network int…
Machine Translation
The automatic translation of text or speech from one human language to another using AI — from early rule-based systems to modern neural mod…
Chatbot
A software application that simulates human conversation — ranging from simple rule-based systems that follow scripted flows to sophisticate…
Technical Concepts
18 termsAlgorithm
A finite, well-defined sequence of instructions or rules that takes an input, performs a series of computational steps, and produces an outp…
Training Data
The dataset used to train a machine learning model — the examples from which the model learns the statistical patterns, relationships, and r…
Test Data
A held-out dataset used exclusively to evaluate a trained model's performance on unseen examples — providing an unbiased estimate of how the…
Loss Function
A mathematical function that quantifies the difference between a model's predictions and the true values — the signal that guides the learni…
Epoch
One complete pass through the entire training dataset during model training — a unit of training progress used to track how many times every…
Batch Size
The number of training examples processed together in a single forward and backward pass during model training — a hyperparameter that balan…
Learning Rate
A hyperparameter that controls the size of the weight updates during gradient descent — determining how quickly or slowly a model learns fro…
Inference
The process of using a trained machine learning model to make predictions or generate outputs on new, unseen data — the production phase tha…
Precision & Recall
Two complementary metrics for evaluating classification models. Precision measures the proportion of positive predictions that are correct;…
Data Augmentation
Techniques that artificially expand a training dataset by creating modified versions of existing data — such as rotating, cropping, or flipp…
Normalization
The process of rescaling data features to a common range or distribution — ensuring that no single feature dominates model training simply b…
API
Application Programming Interface — a standardized set of rules and protocols that allows different software applications to communicate wit…
Edge AI
The deployment of AI models directly on local devices — smartphones, sensors, cameras, vehicles — rather than in the cloud, enabling real-ti…
Latent Space
The abstract, lower-dimensional representation learned by a neural network where data is encoded as points — a compressed space where meanin…
Benchmark
A standardized dataset and evaluation protocol used to measure and compare AI model performance — providing a common yardstick that enables…
Model Compression
A family of techniques that reduce the size, memory footprint, and computational cost of AI models while preserving as much performance as p…
Parameters
The internal variables of a machine learning model that are learned during training — in neural networks, these are primarily the weights an…
Synthetic Data
Artificially generated data that mimics the statistical properties and patterns of real-world data — created to train AI models when real da…
Ethics & Society
11 termsAI Ethics
The field that establishes principles and frameworks to guide the development and deployment of AI systems in ways that are fair, transparen…
Algorithmic Bias
The tendency of AI systems to produce systematically unfair or discriminatory outcomes for certain groups — arising from biased training dat…
Fairness
An AI ethics principle and active research area focused on ensuring AI systems produce equitable outcomes across demographic groups — a goal…
Explainable AI (XAI)
A set of methods and principles aimed at making AI model decisions interpretable and transparent to humans — enabling auditing, debugging, r…
AI Alignment Problem
The fundamental challenge of ensuring that advanced AI systems pursue goals and exhibit behaviors that are genuinely aligned with human valu…
AI Safety
An interdisciplinary research field focused on ensuring that AI systems are reliable, controllable, and beneficial — addressing both near-te…
Technological Singularity
A hypothetical future point at which technological progress — particularly AI-driven recursive self-improvement — becomes so rapid and trans…
Deepfake
Synthetic media — typically video or audio — generated by AI to convincingly depict a real person saying or doing something they never actua…
AI Regulation
The emerging body of laws, policies, and standards that governments and international bodies are developing to govern the development, deplo…
Data Privacy
The principles and practices governing how personal data is collected, stored, processed, and shared in AI systems — ensuring individuals ma…
Responsible AI
A framework of principles and practices for developing and deploying AI systems that are fair, transparent, accountable, safe, and beneficia…
No terms found
Try a different search term or clear your filters.