VisualApps
Browser-based visualisation apps that make AI and machine learning algorithms interactively explorable — no installation, no prior knowledge required.
AI Models Compared
How quickly are AI models becoming more capable? Interactive visualisation of the METR time horizon: how long tasks can various models reliably solve?
Open app →
Neural Network (ANN)
A simple neural network recognises handwritten digits in real time. Weights, activations and learning progress are visualised live.
Open app →
K-Nearest Neighbors (kNN)
Interactive 2D visualisation of the kNN algorithm. Data points can be moved, added and deleted — classification regions adapt in real time.
Open app →
K-Nearest Neighbors 3D
The kNN algorithm in three dimensions — rotatable, zoomable, intuitively explorable. Including a live demo for gesture recognition (scissors, rock, paper).
Open app →
Support Vector Machines (SVM)
Visualisation of one of the most powerful supervised learning methods. Shows how support vectors determine the optimal decision boundary between classes.
Open app →
Decision Tree
The decision tree is trained on training data and displayed graphically. Every decision path can be traced step by step.
Open app →
Naive Bayes
Classification with the Naive Bayes algorithm — well known from spam filters. Shows how categorical features are used probabilistically for class assignment.
Open app →
Linear Regression
Probably the simplest ML method, made interactive. Data points can be placed and moved freely — the regression line adjusts instantly.
Open app →
The VisualApps are created as a teaching and transfer project at the interface between university and industry. They are used in our own teaching at Reutlingen University as well as in corporate training and talks.
Get in touch