What does neural network mean?
A model made of layers of weighted sums and simple squashing functions. Training adjusts the weights so the outputs match the labels.
In a lesson
Nearest neighbour keeps all the data and compares against it every time. A neural network keeps a set of numbers called weights instead, learned from the data once, and the data can then be thrown away. This lesson trains one, in the browser, in about a second.
Learn it
- Taught in 8.4 A tiny network Learning, Robot club