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.
Warm-up
0–5 minPut the question on the board or the screen. Students write one or two sentences in box 1 of the worksheet. Hear two or three ideas, but keep the answer for later.
From the lesson pageThe question (lesson title) What's inside an AI if you open it up?
Explore
5–30 minExplanation · about 8 min
Read the explanation together, and compare it with the guesses from the warm-up.
From the lesson page1 · 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.
Experiment · about 12 min
Open the experiment on the lesson page, on students' devices or the classroom screen. Students note what they changed and what happened in box 2.
From the lesson page2 · Experiment 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.
Figure · about 5 min
Look at the lesson's figure together and walk through the idea once more.
From the lesson pageFigure From input to output, through the layers
A neural network is numbers changing shape as they pass through one layer after another.
Numbers flow from left to right. The orange box in the middle is what makes stacking layers mean something.
Check
30–40 minStudents try the three questions on their own first, then mark them together with the quiz on the lesson page. Read the explanation for any they missed.
From the lesson page3 · Quiz Q1What's closest to what one dot in a neural network does?
- ① Multiplies by weights, adds, checks a threshold
- ② Memorizes whole sentences
- ③ Fetches answers from the internet
- ④ Writes down its own rules in words
Q2Why can a neural network make complex judgments?
- ① Each dot is really smart
- ② Simple math builds up over many layers
- ③ People wrote the answers in advance
- ④ Its screen is big
Q3What does a 'weight' decide?
- ① The size of the text
- ② Screen brightness
- ③ How strong a signal passes
- ④ Internet speed
Show answers and explanations
- Q1 · Answer ① Multiplies by weights, adds, checks a threshold One dot only multiplies, adds, checks the threshold and passes it on. The amazing part doesn't come from one dot — it comes from huge numbers of those dots stacked in layers.
- Q2 · Answer ② Simple math builds up over many layers The first layer only picks up small bits like lines. Those bits become eyes and ears in the next layer, and a cat in the last one. Depth is what makes the judgment.
- Q3 · Answer ③ How strong a signal passes Each link has a different weight, so some signals pass on strongly and others weakly. Training is really just fixing these weight numbers, bit by bit.
Wrap-up
40–45 minRead “today in one line” together. Students rewrite it in their own words in the last box. Two or three read theirs out, and you're done.
From the lesson pageToday in one line One dot can only multiply and add. Stack them in layers, and out comes judgment.
Background reading for you
- 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)