The AI Glossary
Master the concepts driving the future of artificial intelligence. From foundational algorithms to complex neural architectures, navigate the terminology of modern AI.
Fundamentals
4 TermsArtificial Intelligence (AI)
The capability of computer systems to perform tasks typically associated with human intelligence — including learning, reasoning, perception, and decision-making.
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 faces, or translating text — with no ability to generalize beyond that domain.
Artificial General Intelligence (AGI)
A theoretical form of AI with human-level cognitive flexibility — capable of understanding, learning, and solving any intellectual task that a human can, across any domain.
Artificial Superintelligence (ASI)
A hypothetical level of intelligence that would surpass human cognitive capabilities in virtually all domains — from scientific creativity to social reasoning — by an arbitrarily large margin.
Machine Learning
8 TermsMachine Learning (ML)
A subfield of AI that develops algorithms allowing machines to learn patterns from data and make predictions or decisions — without being explicitly programmed for each scenario.
Data Science
An interdisciplinary field combining statistics, programming, and domain expertise to extract knowledge and actionable insights from structured and unstructured data.
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 predictions on new, unseen data.
Unsupervised Learning
A Machine Learning paradigm that works with unlabeled data, discovering hidden patterns, structures, or groupings on its own — without predefined correct answers.
Reinforcement Learning (RL)
A Machine Learning paradigm where an agent learns to make decisions by interacting with an environment, receiving rewards for good actions and penalties for bad ones, seeking to maximize cumulative reward over time.
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 performance than purely supervised or unsupervised approaches alone.
Overfitting
A modeling failure where a machine learning model learns the training data too closely — memorizing noise and edge cases — and subsequently performs poorly on new, unseen data.
Cross-Validation
A model evaluation technique that divides data into multiple subsets, repeatedly training on some and testing on the remainder, to obtain a more reliable, unbiased estimate of model performance.
Feature Engineering
The process of selecting, transforming, or creating input variables (features) from raw data to make machine learning algorithms work more effectively on a given problem.
Hyperparameter Tuning
The process of systematically optimizing the configuration settings of a machine learning algorithm — settings set before training, not learned from data — to maximize model performance.
Deep Learning
10 TermsDeep Learning (DL)
A subfield of Machine Learning that uses artificial neural networks with many layers to learn extremely complex patterns directly from raw data — such as images, audio, and text.
Artificial Neural Network (ANN)
A computational model inspired by the human brain, composed of interconnected layers of nodes (neurons) that process information and learn complex mappings from inputs to outputs.
Activation Function
A mathematical function applied to each neuron's output that introduces non-linearity, enabling neural networks to learn complex, non-linear patterns rather than just linear combinations of inputs.
Backpropagation
The foundational algorithm for training neural networks — it efficiently computes the gradient of the loss function with respect to every weight in the network, enabling gradient-based optimization.
Gradient Descent
An iterative optimization algorithm that minimizes a loss function by updating model parameters in small steps in the direction opposite to the gradient — progressively reducing prediction error.
Convolutional Neural Network (CNN)
A neural network architecture specialized for grid-structured data (especially images) that uses learned filters to detect local features — edges, textures, shapes — in a hierarchical, spatially-aware manner.
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 context from previous inputs when processing each new element.
LSTM / GRU
Advanced Recurrent Neural Network variants that use gating mechanisms to selectively retain or forget information — overcoming the vanishing gradient problem and enabling learning of long-term dependencies in sequences.
Transformer
A neural network architecture that processes entire sequences in parallel using self-attention mechanisms — eliminating recurrence and enabling the large-scale training that underlies modern LLMs and many state-of-the-art AI systems.
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 output — enabling models to capture long-range dependencies without recurrence.
Dropout
A regularization technique that randomly deactivates a fraction of neurons during each training step, forcing the network to learn more robust, distributed representations and reducing overfitting.
Generative AI
8 TermsGenerative AI
A branch of AI focused on models that generate new, original content — text, images, audio, code, video — that is statistically similar to the data they were trained on.
Large Language Model (LLM)
A Transformer-based deep learning model trained on massive text corpora — capable of understanding, generating, translating, summarizing, and reasoning about human language at unprecedented scale.
Generative Adversarial Network (GAN)
A generative model architecture composed of two competing neural networks — a generator that creates synthetic data and a discriminator that attempts to detect fakes — trained together in a minimax game until outputs become indistinguishable from real data.
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, similar data points by sampling from that learned space.
ChatGPT
A conversational AI assistant developed by OpenAI, built on the GPT family of large language models and aligned with human preferences through RLHF — designed for natural, multi-turn dialogue and a wide range of text-based tasks.
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 predict the next token — forming the foundation for ChatGPT and many AI applications.
BERT
Bidirectional Encoder Representations from Transformers — Google's landmark language model that reads text bidirectionally, capturing richer contextual understanding than left-to-right models, and became the foundation for NLP fine-tuning.
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 dataset — leveraging the general knowledge already encoded in the model.
Prompt Engineering
The practice of designing, refining, and structuring inputs (prompts) given to AI language models to elicit the most accurate, relevant, and useful responses — without modifying model weights.
Applications
5 TermsComputer Vision
A field of AI that enables machines to interpret and understand visual information from images and video — detecting objects, recognizing faces, reading scenes, and extracting actionable insights from pixels.
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 — powering applications from chatbots to translation systems.
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 bounding box for each detected instance.
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 belonging to a road, building, sky, person, or any other class.
Sentiment Analysis
An NLP technique that automatically determines the emotional tone or opinion expressed in text — typically classifying it as positive, negative, or neutral — to extract subjective insights at scale.
Named Entity Recognition (NER)
An NLP task that identifies and classifies named entities in text — such as people, organizations, locations, dates, and monetary values — enabling structured extraction from unstructured language.
Ethics & Society
7 TermsAI Ethics
The field that establishes principles and frameworks to guide the development and deployment of AI systems in ways that are fair, transparent, accountable, and respectful of human rights and values.
Algorithmic Bias
The tendency of AI systems to produce systematically unfair or discriminatory outcomes for certain groups — arising from biased training data, flawed model assumptions, or the contexts in which systems are deployed.
Fairness
An AI ethics principle and active research area focused on ensuring AI systems produce equitable outcomes across demographic groups — a goal that involves irresolvable trade-offs between competing mathematical definitions of what 'fair' actually means.
Explainable AI (XAI)
A set of methods and principles aimed at making AI model decisions interpretable and transparent to humans — enabling auditing, debugging, regulatory compliance, and trust in AI systems.
AI Alignment Problem
The fundamental challenge of ensuring that advanced AI systems pursue goals and exhibit behaviors that are genuinely aligned with human values and intentions — especially as systems become more capable and autonomous.
AI Safety
An interdisciplinary research field focused on ensuring that AI systems are reliable, controllable, and beneficial — addressing both near-term risks from current systems and long-term risks from potentially transformative future AI.
Technological Singularity
A hypothetical future point at which technological progress — particularly AI-driven recursive self-improvement — becomes so rapid and transformative that it fundamentally and irreversibly alters human civilization in ways that cannot be predicted from our current vantage point.
Technical Concepts
8 TermsAlgorithm
A finite, well-defined sequence of instructions or rules that takes an input, performs a series of computational steps, and produces an output — the foundational building block of all computing and AI systems.
Training Data
The dataset used to train a machine learning model — the examples from which the model learns the statistical patterns, relationships, and representations it will use to make predictions on new data.
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 model will perform in the real world.
Loss Function
A mathematical function that quantifies the difference between a model's predictions and the true values — the signal that guides the learning process by telling the model how wrong it is and in which direction to improve.
Epoch
One complete pass through the entire training dataset during model training — a unit of training progress used to track how many times every training example has been seen by the model.
Batch Size
The number of training examples processed together in a single forward and backward pass during model training — a hyperparameter that balances training speed, memory usage, and gradient estimate quality.
Learning Rate
A hyperparameter that controls the size of the weight updates during gradient descent — determining how quickly or slowly a model learns from its training data.
Inference
The process of using a trained machine learning model to make predictions or generate outputs on new, unseen data — the production phase that follows training and deployment.