[{"content":"Easing Functions Cheat Sheet is an interactive reference for comparing easing functions that control how animation values change over time. It lists Sine, Quad, Cubic, Quart, Quint, Expo, Circ, Back, Elastic, Bounce, and related variants, making it easy to compare the shape and behavior of each In, Out, and InOut curve.\nSelecting a function reveals the corresponding CSS transition-timing-function value, PostCSS usage, gradient application, and TypeScript implementation. The live samples compare the selected easing against a linear function for size, position, and opacity, which makes the site useful when choosing motion timing for UI animation.\neasings.explorable-explanations.comEasing Functions Cheat SheetA cheat sheet for comparing easing functions such as Sine, Quad, Expo, and Bounce through curves, CSS, and TypeScript code.easings.explorable-explanations.com ","date":"2026-06-24T00:00:00Z","image":"https://explorable-explanations.com/p/easings/images/cover_hu_8cf8aaf2bc0c8d18.png","permalink":"https://explorable-explanations.com/en/p/easings/","title":"Easing Functions Cheat Sheet"},{"content":"Map Tile Browser is an interactive tool for seeing how web map tiles are divided directly on a map. As you change the zoom level, it shows the visible tile grid and labels each tile with its center coordinates, zoom level, tile coordinates, and Quadkey.\nThe tool also includes place search and map style switching, so you can compare Carto basemaps with GSI standard, pale, and aerial-photo maps while inspecting tile structure. Clicking a tile copies its information, which makes the site useful both for map application development and for explaining how map tiles work.\nwhat-the-tile.explorable-explanations.comMap Tile BrowserAn interactive tool for inspecting map tile bounds, coordinates, and Quadkeys at each zoom level.what-the-tile.explorable-explanations.com ","date":"2026-06-18T00:00:00Z","image":"https://explorable-explanations.com/p/what-the-tile/images/cover_hu_1c58ffc4bfe51139.png","permalink":"https://explorable-explanations.com/en/p/what-the-tile/","title":"Map Tile Browser"},{"content":"TensorFlow Playground is interactive content that lets you train a small neural network in the browser and experiment with datasets, features, hidden layers, neuron counts, activation functions, regularization, and learning rates.\nAs training progresses, you can observe how the decision boundary and the representations learned by each neuron change. It is a useful tool for building intuition about neural network learning, overfitting, feature engineering, and model capacity.\ntensor-playground.explorable-explanations.comTensorFlow PlaygroundChange features and layer structure while observing neural network learning and decision boundaries.tensor-playground.explorable-explanations.com ","date":"2026-06-04T00:00:00Z","image":"https://explorable-explanations.com/p/tensor-playground/images/cover_hu_152ab7cc955aca61.png","permalink":"https://explorable-explanations.com/en/p/tensor-playground/","title":"TensorFlow Playground"},{"content":"Embedding Projector is interactive content for projecting high-dimensional embedding vectors into 2D or 3D and exploring their structure as a point cloud. Using projections such as PCA and t-SNE, you can inspect neighborhoods, clusters, and outliers.\nSelecting a point reveals metadata and nearby points, and the interface also supports labels, color coding, night mode, 3D labels, and range selection. It is a useful learning tool for investigating how embedding spaces organize words, images, text, and other data used by machine learning models.\nembedding-projector.explorable-explanations.comEmbedding ProjectorProject high-dimensional embeddings into 2D or 3D and interactively explore clusters and nearest neighbors.embedding-projector.explorable-explanations.com ","date":"2026-05-27T00:00:00Z","image":"https://explorable-explanations.com/p/embedding-projector/images/cover_hu_437af9ebe6baa889.png","permalink":"https://explorable-explanations.com/en/p/embedding-projector/","title":"Embedding Projector"},{"content":"This interactive content projects face photos or GeoJSON data so you can compare distortion across map projections. By switching between projections such as Mercator, Mollweide, Equal Earth, and azimuthal equidistant, you can immediately see how shapes and areas change.\nIt supports PNG and JPEG uploads as well as webcam input and sample data. Graticules and projection descriptions can also be displayed, making it a practical learning demo for map projections. The site also states that images captured with the webcam are not saved on the server.\nprojection-face-photo.vercel.appLearning Map Projections with Face PhotosCompare distortion across map projections using face photos, webcam input, or GeoJSON.projection-face-photo.vercel.app ","date":"2026-05-19T00:00:00Z","image":"https://explorable-explanations.com/p/projection-face-photo/images/cover_hu_9c16a0d3606a76a4.png","permalink":"https://explorable-explanations.com/en/p/projection-face-photo/","title":"Learning Map Projections with Face Photos"},{"content":"This interactive content compares classification methods used in GIS and choropleth maps against the same data. You can view quantile, equal interval, natural breaks (Jenks), standard deviation, geometric interval, head/tail breaks, pretty breaks, and arithmetic progression classifications side by side.\nThe data distribution can be switched between uniform, normal, right-skewed, and bimodal patterns, making it easier to see how the shape of the data changes the resulting classes. Color palettes and the number of classes can also be adjusted, so the demo works well as a learning tool for understanding how classification affects map representation.\nclassification.explorable-explanations.comVisualizing Classification MethodsA demo for comparing quantile, natural breaks, standard deviation, and other classification methods on the same map and histogram.classification.explorable-explanations.com ","date":"2026-05-19T00:00:00Z","image":"https://explorable-explanations.com/p/classification/images/cover_hu_14350e2ddec8b138.png","permalink":"https://explorable-explanations.com/en/p/classification/","title":"Visualizing Classification Methods"},{"content":"AI Explorables is a collection of interactive explainers about AI and machine learning from Google PAIR. It turns abstract topics such as model behavior, datasets, bias, privacy, and text generation into experiences you can explore directly.\nEach piece lets you change inputs or conditions with sliders, choices, and visualized data distributions, then see how the results respond. It is a useful entry point for learning the relationship between models and data without treating AI as a black box.\nai-explorables.explorable-explanations.comAI ExplorablesA collection of interactive explainers for learning AI concepts and social impacts through explorable visualizations.ai-explorables.explorable-explanations.com ","date":"2026-02-01T00:00:00Z","image":"https://explorable-explanations.com/p/ai-explorables/images/cover_hu_9daa13c697c3fe8b.png","permalink":"https://explorable-explanations.com/en/p/ai-explorables/","title":"AI Explorables"},{"content":"An Introduction to Network Analysis and Representation is an interactive learning resource for exploring network data made of nodes and edges. You can switch between examples such as random graphs, character relationships in literature, and transportation networks to observe different structures.\nThe tool lets you experiment with force-directed layouts, gravity, link attraction, node repulsion, degree-based sizing, centrality, clustering coefficients, path finding, and ego networks. It is useful for learning how network diagrams are formed and what common network metrics mean through direct interaction.\nelijahmeeks.comAn Introduction to Network Analysis and RepresentationAn interactive resource for learning network layout, centrality, clustering, and path finding.elijahmeeks.com ","date":"2026-02-01T00:00:00Z","image":"https://explorable-explanations.com/p/learning-network-visualization/images/cover_hu_73e8ee926cdf00.png","permalink":"https://explorable-explanations.com/en/p/learning-network-visualization/","title":"An Introduction to Network Analysis and Representation"},{"content":"CNN Explainer is interactive content that traces how a convolutional neural network (CNN) classifies an image through layer-by-layer visualization. You can see how the input image is transformed through convolution, activation, pooling, and fully connected layers.\nBecause filters, feature maps, neuron activations, and final prediction probabilities are shown in the same context, the tool makes it easier to connect the model structure with the flow of inference. It is a useful learning tool for explaining what happens inside an image recognition model.\npoloclub.github.ioCNN ExplainerAn interactive visualization tool for observing feature extraction and classification through each layer of a CNN.poloclub.github.io ","date":"2026-02-01T00:00:00Z","image":"https://explorable-explanations.com/p/cnn-explainer/images/cover_hu_74fac71aaa6f6d6d.png","permalink":"https://explorable-explanations.com/en/p/cnn-explainer/","title":"CNN Explainer"},{"content":"Diffusion Explainer breaks down how Stable Diffusion generates images from text prompts into interactive steps. It shows the main stages of the process: tokenizing and encoding text, refining an image representation from noise, and upscaling the image.\nBy switching prompts, you can observe how text and image representations connect to the generated result. It is a useful tool for building an intuitive understanding of diffusion models and image generation AI before going deeper into formulas or implementation details.\ndiffusion-explainer.explorable-explanations.comDiffusion ExplainerA tool that visualizes Stable Diffusion as text representation, denoising, and upscaling stages.diffusion-explainer.explorable-explanations.com ","date":"2026-02-01T00:00:00Z","image":"https://explorable-explanations.com/p/diffusion-explainer/images/cover_hu_b45d5d3c9c5b5c39.png","permalink":"https://explorable-explanations.com/en/p/diffusion-explainer/","title":"Diffusion Explainer"},{"content":"GAN Lab is an interactive visualization tool for observing the training process of a generative adversarial network (GAN) in the browser. On a 2D data distribution, you can watch the generator create samples while the discriminator learns to distinguish real from fake examples through changes in points and decision boundaries.\nBy changing the distribution shape, model structure, and learning speed, you can try cases where GAN training stabilizes or breaks down. It is a useful learning tool for understanding the roles of the generator and discriminator and the competitive relationship between them.\nganlab.explorable-explanations.comGAN LabExperiment with and observe GAN generator and discriminator training on 2D data distributions.ganlab.explorable-explanations.com ","date":"2026-02-01T00:00:00Z","image":"https://explorable-explanations.com/p/ganlab/images/cover_hu_24b6c12ae425185.png","permalink":"https://explorable-explanations.com/en/p/ganlab/","title":"GAN Lab"},{"content":"How to Use t-SNE Effectively is an interactive article about how to interpret t-SNE, a common method for visualizing high-dimensional data. It shows how cluster size, distances between clusters, randomness, and perplexity can affect the appearance of a plot.\nBy changing sample data and parameters, you can see that the same dataset can produce very different visual results. The article is an important learning resource for understanding what can be trusted in a t-SNE plot and what should not be overinterpreted.\npost-misread-tsne.explorable-explanations.comHow to Use t-SNE EffectivelyLearn how parameters and data structure affect t-SNE plots so you do not misread them.post-misread-tsne.explorable-explanations.com ","date":"2026-02-01T00:00:00Z","image":"https://explorable-explanations.com/p/post--misread-tsne/images/cover_hu_42f0327d842d30c7.png","permalink":"https://explorable-explanations.com/en/p/post--misread-tsne/","title":"How to Use t-SNE Effectively"},{"content":"MLU-Explain is a set of visual machine learning explainers from Amazon Machine Learning University. It covers foundational topics such as decision trees, random forests, linear regression, logistic regression, neural networks, cross validation, bias, and variance.\nInstead of relying only on formulas, each article uses visualizations of data points, decision boundaries, model outputs, and evaluation metrics. It is a useful series for beginners who want an intuitive grasp of what happens when models are selected, trained, and evaluated.\nmlu-explain.github.ioMLU-ExplainInteractive visual explainers for learning the basic concepts of machine learning.mlu-explain.github.io ","date":"2026-02-01T00:00:00Z","image":"https://explorable-explanations.com/p/aws-mlu-explain/images/cover_hu_ee1f50fa882e649.png","permalink":"https://explorable-explanations.com/en/p/aws-mlu-explain/","title":"MLU-Explain"},{"content":"MNIST MLP Inference Visualization is an interactive tool for observing the inference process of a handwritten digit recognition model in 3D. When you draw a digit on a 28 by 28 grid, you can see how activations propagate through each layer of a trained multilayer perceptron (MLP) and become final prediction probabilities.\nNeuron activations, strong weighted connections, prediction distributions, and the training timeline are shown in the same view, making the internal representation of a neural network easier to understand visually. It is useful for learning image classification inference beyond just the input and output.\nnn-playground.explorable-explanations.comMNIST MLP Inference VisualizationDraw handwritten digits and observe MLP activations and prediction probabilities in 3D.nn-playground.explorable-explanations.com ","date":"2026-02-01T00:00:00Z","image":"https://explorable-explanations.com/p/neural-network-visualisation/images/cover_hu_197f6c13d75a3467.png","permalink":"https://explorable-explanations.com/en/p/neural-network-visualisation/","title":"MNIST MLP Inference Visualization"},{"content":"Parable of the Polygons is an interactive article about how small individual preferences can create large-scale social segregation. By moving triangle and square residents, you can observe how segregation can emerge even when individuals do not hold strong biases.\nThe article gradually introduces manual movement, automated simulation, tolerance changes, and anti-conformity. It is a representative explorable for understanding social segregation as the accumulation of simple rules rather than as an abstract argument.\nncase.meParable of the PolygonsAn interactive simulation for learning how small individual preferences can lead to social segregation.ncase.me ","date":"2026-02-01T00:00:00Z","image":"https://explorable-explanations.com/p/polygons/images/cover_hu_dfa21e74d38a8e61.png","permalink":"https://explorable-explanations.com/en/p/polygons/","title":"Parable of the Polygons"},{"content":"Transformer Explainer is an interactive visualization tool for following the internal processing of a text generation model token by token. You can see how input text is tokenized, embedded, combined with position information, processed through attention and feed-forward layers, and used to predict the next token.\nBy looking at self-attention weights and intermediate representations, you can observe how a Transformer refers to context. It is a useful learning tool for understanding the foundation of large language models as an actual text generation process, not only through formulas or implementation details.\ntransformer-explainer.explorable-explanations.comTransformer ExplainerInteractively follow Transformer tokenization, attention, intermediate representations, and next-token prediction.transformer-explainer.explorable-explanations.com ","date":"2026-02-01T00:00:00Z","image":"https://explorable-explanations.com/p/transformer-explainer/images/cover_hu_2aaf9633f0eb174d.png","permalink":"https://explorable-explanations.com/en/p/transformer-explainer/","title":"Transformer Explainer"},{"content":"Vega-Altair is a Python library for creating statistical visualizations declaratively. By combining data, encodings, marks, transforms, and interactions, you can build Vega-Lite-based charts with concise code.\nIt supports not only basic charts such as scatter plots, bar charts, and line charts, but also facets, aggregation, filtering, selections, and tooltips through a consistent grammar. It is a practical way to learn reproducible visualization specifications while doing data analysis in Python.\naltair-viz.github.ioVega-AltairA Vega-Lite-based Python library for creating declarative statistical visualizations.altair-viz.github.io ","date":"2026-02-01T00:00:00Z","image":"https://explorable-explanations.com/p/altair/images/cover_hu_b838a584f005ed02.png","permalink":"https://explorable-explanations.com/en/p/altair/","title":"Vega-Altair"}]