← All topics
Foundations
Forward Propagation
Follow weighted sums and activations through a 2–2–1 network.
A forward pass turns inputs into a prediction, one layer at a time.
Why do we need this? Every neural-network prediction is built from these layer-by-layer calculations.
Positive weightNegative weightActive signal →← Backward gradient
STEP 1 OF 3
Inputs enter the network
The input layer holds the measured features. It passes these values to the hidden layer.
No account required. Local images and model files stay in your browser. Educational models demonstrate mechanisms; they are not production predictors.