Loading slide
The dog example is small. But the pattern it shows is not.
A nose neuron doesn't know what sound is. An ear neuron doesn't know what smell is. A neuron in the middle doesn't know what a dog is, or what danger means, or what barking is for. Each one just receives numbers, multiplies them by weights, and decides whether to fire.
And yet, wired together in the right way, they produce something that looks like judgment.
This is the same pattern that runs through everything in this course. A transistor is just a switch, on or off, nothing more. But millions of them, connected in the right way, run software. A single rule can't capture how language works. But billions of weighted connections, trained on enough text, produce something that can hold a conversation.
The pattern has a name: emergence. A property that none of the parts have on their own, but that appears once enough of them come together.
Once you see it, you find it everywhere. One water molecule is not wet. Wetness is not a thing a single molecule can be. It only appears when trillions of them move together. No single starling decides the shape of the flock, yet thousands of them sweep across the sky as one shifting form. No ant knows the plan, yet the colony builds, farms, and defends itself. A crowd of people can do things no single person in it ever would.
In every case, the magic isn't in the pieces. It's in how they connect.
One neuron, one ceiling. But the ceiling of one is not the ceiling of many.
Connect enough neurons. Train them on enough examples. Something emerges that none of the individual pieces contains.
Intelligence?
Something to sit with