Your next step
A neural network, one small part at a time
Trace a numerical model through connected layers.
Start learningWhat you’ll learn
Turn observations into numbers
Interpret a simple numeric representation.
About 4 minutes · Open activity
A weight changes influence
Predict how an input's weight changes a toy output.
About 4 minutes · Open activity
A bias shifts the starting point
Distinguish a numeric bias term from an input weight.
About 4 minutes · Open activity
A node combines inputs
Trace inputs through one simple computing node.
About 4 minutes · Open activity
A bend makes richer patterns possible
Explain why a nonlinear activation changes what a network can represent.
About 4 minutes · Open activity
Layers build on earlier representations
Identify how one layer's output becomes another's input.
About 4 minutes · Open activity
Deep means multiple learned layers
Interpret deep learning without an intelligence ranking.
About 4 minutes · Open activity
Parameters and temporary signals
Distinguish stored learned settings from values produced for one input.
About 4 minutes · Open activity
Follow the small network
Trace an unseen parcel through a supplied diagram, change one influence, and identify parameters versus temporary values.
About 5 minutes · Open activity