AI Models on Explorable Explanations

TensorFlow Playground

Thu, 04 Jun 2026 00:00:00 +0000

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.

As 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.

tensor-playground.explorable-explanations.com

TensorFlow Playground

Change features and layer structure while observing neural network learning and decision boundaries.

tensor-playground.explorable-explanations.com

Embedding Projector

Wed, 27 May 2026 00:00:00 +0000

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.

Selecting 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.

embedding-projector.explorable-explanations.com

Embedding Projector

Project high-dimensional embeddings into 2D or 3D and interactively explore clusters and nearest neighbors.

embedding-projector.explorable-explanations.com

CNN Explainer

Sun, 01 Feb 2026 00:00:00 +0000

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.

Because 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.

poloclub.github.io

CNN Explainer

An interactive visualization tool for observing feature extraction and classification through each layer of a CNN.

poloclub.github.io

Diffusion Explainer

Sun, 01 Feb 2026 00:00:00 +0000

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.

By 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.

diffusion-explainer.explorable-explanations.com

Diffusion Explainer

A tool that visualizes Stable Diffusion as text representation, denoising, and upscaling stages.

diffusion-explainer.explorable-explanations.com

GAN Lab

Sun, 01 Feb 2026 00:00:00 +0000

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.

By 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.

ganlab.explorable-explanations.com

GAN Lab

Experiment with and observe GAN generator and discriminator training on 2D data distributions.

ganlab.explorable-explanations.com

MLU-Explain

Sun, 01 Feb 2026 00:00:00 +0000

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.

Instead 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.

mlu-explain.github.io

MLU-Explain

Interactive visual explainers for learning the basic concepts of machine learning.

mlu-explain.github.io

Transformer Explainer

Sun, 01 Feb 2026 00:00:00 +0000

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.

By 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.

transformer-explainer.explorable-explanations.com

Transformer Explainer

Interactively follow Transformer tokenization, attention, intermediate representations, and next-token prediction.

transformer-explainer.explorable-explanations.com