Watch nodes randomly drop during training, then see full network activate at inference — with weight scaling
Dropout Rate p
p0.50
50% — each hidden node drops independently
Network Architecture
input – hidden – output nodes
Simulation
SpeedMed
Inverted Dropout
ĥ = (h ⊙ Bern(1−p)) / (1−p)
Key Concepts ▾
What's happening?
Set dropout rate p and press Forward Pass. Each pass samples a fresh random mask — active nodes are scaled by 1/(1−p) so the expected output stays constant regardless of how many nodes survive.