Home▸Machine Learning & Neural Networks▸Federated Learning: Train Without Sharing Data (2D)

Federated Learning: Train Without Sharing Data (2D)

2D federated-learning lab: broadcast, local-train, upload and aggregate rounds play out on a flat client ring, with dropout rate and local-epoch controls driving a live accuracy curve.

Machine Learning & Neural Networks2DModerate60 FPS📱 Mobile-adapted⇄ 3D version

This 2D companion drives the same round structure as the 3D version — broadcast, local train, upload, aggregate — on a flat client ring instead of an orbitable scene, with client count, round speed, dropout rate and local-epochs all exposed as live sliders next to a running accuracy readout.

⚙ Under the hood

2D federated-learning lab: broadcast, local-train, upload and aggregate rounds on a flat client ring, with dropout rate and local-epoch controls driving a live accuracy curve.

federated learningdistributed machine learningprivacy-preserving mlmodel aggregationfedavg

2D · HTML5 Canvas 2D · 60 FPS target · runs fully client-side, no install