AI & Machine Learning Visualizer

Master AI and ML concepts through interactive visualizations. Watch neural networks learn, see algorithms in action, and build intuition for complex ideas.

All visualizations

Every interactive visualization in AI & Machine Learning.

Simple Perceptron

Beginner

Understand the building block of neural networks

WeightsBiasActivationLinear Classification
Open

Backpropagation

Intermediate

See how neural networks learn through gradient descent

Chain RuleGradientsWeight UpdatesLearning
Open

Activation Functions

Beginner

Compare different activation functions and their properties

SigmoidReLUTanhSoftmax
Open

Multi-Layer Perceptron

Intermediate

Build and train a complete feedforward neural network

Hidden LayersForward PassTrainingNon-linearity
Open

Image Filters

Beginner

Apply various filters to images and see real-time results

ConvolutionGaussian BlurSharpenEdge Detection
Open

Edge Detection

Intermediate

Understand Sobel, Canny, and other edge detection algorithms

SobelCannyPrewittLaplacian
Open

Object Detection

Advanced

Learn how neural networks detect objects in images

YOLOR-CNNBounding BoxesNMS
Open

Image Segmentation

Advanced

Visualize semantic and instance segmentation techniques

U-NetMask R-CNNSemantic SegmentationInstance Segmentation
Open

Convolutional Neural Networks

Intermediate

Step a kernel across an image to build feature maps, then pool and stack layers

ConvolutionFeature MapsPoolingStride & Padding
Open

Recurrent Neural Networks

Intermediate

Unroll an RNN through time and watch the hidden state and vanishing gradients

Hidden StateUnrollingVanishing GradientsLSTM
Open

Self-Attention & Transformers

Advanced

See queries, keys and values combine into an attention heatmap for a sentence

Self-AttentionQuery/Key/ValueSoftmaxMulti-Head
Open

Tokenization (BPE)

Beginner

Watch byte-pair encoding merge characters into subword tokens step by step

BPESubwordsVocabularyMerges
Open

Word Embeddings

Intermediate

Explore words as vectors, cosine similarity and analogies like king − man + woman

Word2VecCosine SimilarityAnalogiesVector Space
Open

Text Generation & Sampling

Intermediate

Adjust temperature, top-k and top-p and see how they reshape next-token probabilities

TemperatureTop-kTop-pSoftmax
Open

Multi-Armed Bandit

Beginner

Compare ε-greedy, UCB and Thompson sampling on slot machines with hidden payouts

Explorationε-GreedyUCBRegret
Open

Value Iteration

Intermediate

Watch state values and the optimal policy emerge in a grid world with the Bellman equation

Bellman EquationMDPDiscount FactorPolicy
Open

Q-Learning

Intermediate

Train an agent to reach a goal by trial and error and watch its Q-table fill in

Q-TableTemporal DifferenceLearning RateEpisodes
Open

K-Means Clustering

Beginner

Step through assigning points to centroids and moving centroids to the mean

ClusteringCentroidsElbow MethodUnsupervised
Open

K-Nearest Neighbors

Beginner

Classify a point by majority vote of its neighbours and see the decision boundary change with k

ClassificationDistance MetricsDecision BoundaryOverfitting
Open

Decision Trees

Intermediate

Grow a tree split by split using Gini impurity and see how it partitions the plane

Gini ImpurityInformation GainDepthOverfitting
Open

Gradient Descent

Intermediate

Roll down a loss surface and compare learning rates, momentum and Adam

Learning RateMomentumAdamLoss Surface
Open

Why learn AI & ML?

Master the technology shaping our future.

Future of technology

AI is changing every industry, from healthcare and finance to autonomous vehicles and research.

High-demand career

AI/ML engineers are among the most sought-after professionals.

Solve real problems

Build systems that diagnose diseases, predict trends, and automate complex tasks.

Interdisciplinary

Combines mathematics, statistics, computer science, and domain expertise.

Learning features

Everything you need to master AI and ML concepts.

Visual neural networks

See neurons activate and backpropagation update weights in real time.

Live training

Watch models learn with loss curves, accuracy metrics, and gradient flows.

Interactive parameters

Adjust learning rates, architectures, and hyperparameters and see the effect.