Tools Categories New Featured Glossary

Submit a toolSubmit

Loading…

A directory of AI tools, sorted into clear categories with pricing, platforms and alternatives side by side.

ExploreAll tools Categories New Featured Glossary

For makersSubmit a tool Update a listing Contact us

LegalTerms Privacy

Some links are affiliate links: we may earn a small commission if you buy through them, at no extra cost to you. Affiliate cards are marked “Opens site”. All images, videos and other content belong to their creators and original sources. If something here is wrong or you would like it removed, please contact us.

© 2026 BroUseAI

Home
Glossary
Machine learning

Machine learning and deep learning terms

How machines learn from data: training, neural networks, supervised and reinforcement learning, overfitting and the building blocks of deep learning. 28 terms

All terms 162 AI basics 17 Generative AI and LLMs 22 Chatbots and assistants 14 Prompts and settings 16 Images, video, audio and writing 17 Agents and automation 13 Machine learning 28 Building and running AI 14 Ethics, safety and privacy 21

Search the glossary

28 terms

A

Activation functionAn activation function decides how strongly each unit in a neural network passes its signal on, which lets the network learn complex, non-linear patterns.Attention mechanismAn attention mechanism lets an AI model focus on the most relevant parts of its input, such as which earlier words matter for understanding the current one.

B

BackpropagationBackpropagation is how a neural network learns from mistakes: it works backwards from the error to find how much each connection caused it, then adjusts them.

C

ClassificationClassification is a machine learning task where the model sorts things into categories, such as “spam” or “not spam”, or which animal is in a photo.ClusteringClustering is a machine learning technique that groups similar items together without being told the groups in advance.Convolutional neural network (CNN)A convolutional neural network (CNN) is a type of neural network designed for images. It scans a picture in small patches to detect edges, shapes and objects.

D

Data augmentationData augmentation creates extra training examples by changing existing ones, such as flipping, cropping or recolouring photos, to help a model generalise.DatasetA dataset is an organised collection of data, such as a table of house prices or a folder of labelled photos, used to train or test AI models.Deep learningDeep learning is a type of machine learning that uses neural networks with many layers to learn complex patterns in text, images and sound.Dimensionality reductionDimensionality reduction simplifies data with many features into fewer, while keeping the most important information, so it is easier to analyse or visualise.

F

Federated learningFederated learning trains an AI model across many devices, such as phones, without collecting their data in one place. Only model updates are shared.

G

Generative adversarial network (GAN)A generative adversarial network (GAN) is two neural networks that compete: one creates fake images and the other tries to spot them, so both keep improving.Gradient descentGradient descent is the method most AI models use to learn: it repeatedly nudges the model’s settings in the direction that reduces its errors.

H

HyperparameterA hyperparameter is a setting chosen before training an AI model, such as how fast it learns or how many layers it has, that shapes how training goes.

L

Loss functionA loss function measures how wrong an AI model’s predictions are during training. Training tries to make this number as small as possible.

M

Machine learning (ML)Machine learning (ML) is a way of building AI where computers learn patterns from examples, instead of being given step-by-step rules.

N

Neural networkA neural network is an AI model made of layers of connected units, loosely inspired by the brain, that learns by adjusting the strength of its connections.

O

OverfittingOverfitting is when an AI model learns its training examples too closely, including their noise, so it does well on them but poorly on new data.

P

ParametersParameters are the internal numbers an AI model learns during training. A model’s size, such as “70 billion parameters”, counts them.

R

Recurrent neural network (RNN)A recurrent neural network (RNN) is a type of neural network that reads data in sequence, one step at a time, keeping a memory of what came before.RegressionRegression is a machine learning task where the model predicts a number, such as a house price, tomorrow’s temperature or next month’s sales.Reinforcement learning (RL)Reinforcement learning (RL) trains an AI by trial and error: it takes actions, gets rewards or penalties, and learns which choices lead to the best results.

S

Self-supervised learningSelf-supervised learning is when an AI model creates its own practice questions from raw data, like hiding a word in a sentence and learning to predict it.Supervised learningSupervised learning trains an AI model on examples that come with the right answer, such as photos labelled “cat” or “dog”, so it can label new examples.Synthetic dataSynthetic data is artificial data generated by computers, often by AI, to train or test models when real data is scarce, expensive or private.

T

Training dataTraining data is the set of examples, such as text, images or past records, that an AI model learns from. Its quality and range shape what the model can do.Transfer learningTransfer learning reuses what an AI model learned on one task as the starting point for a related task, so the new task needs much less data and training.

U

Unsupervised learningUnsupervised learning finds patterns and groups in data that has no labels, such as discovering types of customers from their shopping habits.

Browse related tools

AI tools listed on BroUseAI that put these ideas to work.

AI Models & Infrastructure Data Analysis

Featured

CommentWatchDogHide and delete spam comments on Facebook and Instagram ads

C2PA RemoverCheck and remove C2PA content credentials

WasItAIDetect whether an image was AI-generated or camera-captured.

Claude Mark RemoverRemove hidden Claude marks and humanize AI-generated text.

GenjutsuTransform one video into endless variations with AI.

Token360One API for 80+ frontier AI models across text, image, audio and video.

Answer Engine OptimizationSee how AI answer engines mention and cite your website.

Adobe Firefly Background RemoverAI tool that removes photo backgrounds and outputs a transparent PNG — free to use.

SeedRouterAccess image, video, and language models via one API without monthly subscriptions

AI Image HumanizerHumanize AI-generated images while preserving their visible appearance

AI Overviews TrackerTrack website mentions and citations across six AI engines