Music Genre Classifier: k-NN Decision Map and Leave-One-Out Curve
A flat map of the same k-NN classifier: the decision regions in the tempo and brightness plane, every labelled record as a small vinyl disc, and the new track with lines to its k neighbours. Leave-one-out accuracy against k and the neighbour distances are plotted live. Same shared model and numerical checks as the 3D version.
Drop a new track into a 3D cloud of labelled records, arranged by tempo, spectral centroid and percussiveness, and watch a real k-nearest-neighbours classifier pick its closest neighbours and vote. Change the track, k, the distance metric and the vote weighting and see the decision slice, the confidence, the leave-one-out accuracy and the best k, with built-in numerical checks. Turntable, records and speaker modelled in Blender; the data are synthetic.
A flat map of the same k-NN classifier: the decision regions in the tempo and brightness plane, every labelled record as a small vinyl disc, and the new track with lines to its k neighbours. Leave-one-out accuracy against k and the neighbour distances are plotted live. Same shared model and numerical checks as the 3D version.
2D · HTML5 Canvas 2D · 60 FPS target · runs fully client-side, no install