What's inside an AI if you open it up? — Neural networks
One dot can only multiply and add. Stack them in layers, and out comes judgment.
1 · Think first
Inside an AI are dots stacked in layers, passing numbers to each other. That's called a neural network.
What one dot does is surprisingly simple. It multiplies the incoming numbers by weights and adds them all up, and if the total clears a threshold, it passes it on to the next layer.
The smarts aren't inside any one dot. As the numbers pass through layer after layer, simple math piles up into complex judgments.
2 · Experiment · Put it in order
Try it — What happens inside a neural network, in order
Tap the mixed-up pieces in the right order. Three sets: what one dot does, the path through the layers, and how the weights get set.
Tap the pieces below in the order you think is right.
Figure
From input to output, through the layers
A neural network is numbers changing shape as they pass through one layer after another.
3 · Quiz
Quick check
Three questions. Pick an answer and it's marked right away, with the reason why.
Today in one line
Today in one line
One dot can only multiply and add.
Stack them in layers, and out comes judgment.
Learn more
- A summary written by three of the people who built deep learning. Lots of figures, so it's easy to skim. — Deep learning (Nature, 2015)
- The first paper to treat nerve cells as units of calculation, back in 1943 — where the idea of a neural network started. — McCulloch & Pitts, A logical calculus of the ideas immanent in nervous activity (1943)
- The 1986 paper that made the method of fixing weights by the error (backpropagation) widely known. — Learning representations by back-propagating errors (1986)