Layers & Forward Propagation
You'll be able to
- Understand input, hidden, and output layers
- Trace a signal through a network
- Explain why depth adds power
Stacking neurons into layers creates a neural network. The input layer receives raw data, hidden layers transform it into increasingly abstract features, and the output layer produces a prediction.
Forward propagation is the process of moving a signal layer by layer: each layer computes a weighted sum of its inputs, applies an activation, and passes the result to the next. Depth lets the network learn hierarchies — edges, then shapes, then objects.
Challenge
Trace the signal
Describe, in your own words, the journey of one pixel's values from the input layer to a final 'dog' decision.
Knowledge Check
Layers
Which layer produces the final prediction of a network?
Forward propagation describes sending data through the network from input to output.
Answer all questions to submit.