Neural Network, Explained in Plain Language

A machine that learns by getting things wrong.

Dots and lines #

Dots hold a number. Lines carry it to the next dot. That's the whole machine.

In one end, out the other #

Numbers go in one side. An answer comes out the other.

Every line has a dial #

Turn a dial up and that line matters more. A big network has millions of dials.

At first, it's wrong #

All the dials start at random. So the first guess is nonsense.

So nudge the dials #

Every dial that pushed toward "dog" gets turned down a hair. A hair. Not a lot.

Now do that a million times #

Forward, then backward. Forward, then backward. Do that a million times and the dials settle somewhere that works. That's learning.