Loading 3D scene…
XYZbasis vectors (solid = original, dashed = transformed)
Matrix Transformations in 3D - Interactive Visualization
Every neural network layer applies a matrix transformation to its input vectors. This visualizer makes the abstract concrete: enter a 3×3 matrix and watch it reshape a unit cube in 3D space. Presets show the five most important transformation types used in machine learning and computer graphics.
- Rotation matrices: see how orthogonal matrices preserve distances and angles
- Scale matrices: understand how diagonal matrices stretch or compress space
- Shear transformations: key to understanding affine transformations in CNNs
- Singular matrices: watch space collapse when the determinant is zero
- Basis vectors X, Y, Z and their transformed equivalents shown as colored arrows
- Foundation for PCA, SVD, attention mechanisms, and all of deep learning
Part of the EngineersOfAI Interactive 3D - free interactive visualizations covering every major concept in machine learning and AI engineering. Hover any element for a plain-English explanation. No code required.