Loading slide

The Neuron Idea

  1. 01The Neuron Idea
  2. 02A familiar idea
  3. 03Same era, different bet
  4. 04A neuron, at its simplest
  5. 05Adding things up
  6. 06The first artificial neuron
  7. 07Strength, not just presence
  8. 08The signal itself has a strength
  9. 09Multiply, then add
  10. 10Just a recipe
  11. 11What a weight really is
  12. 12Where the numbers come from
  13. 13Back to the real thing
  14. 14The Perceptron
  15. 15How it learned
  16. 16What training actually is
  17. 17Why this was different
  18. 18What Rosenblatt claimed
  19. 19The shape of hype
  20. 20Twelve years of real work
  21. 21The verdict
  22. 22What the proof didn't say
  23. 23What it could do
  24. 24What it could not do
  25. 25The reason
  26. 26The limit was real
  27. 27Before we go further
  28. 28Memory card
  29. 29What if we added another?
  30. 30Many dumb things
  31. 31Layers
  32. 32More Layers
  33. 33The whole thing
  34. 34A network of neurons
  35. 35A small group kept going
  36. 36Reinforce your understanding
  37. 37Question: What is learning?
  38. 38Question: The limit
  39. 39Question: Training a network
  40. 40Quiz: answer
  41. 41The idea didn't die. It waited.
  42. 42Want to go deeper?
30 / 41
BackNext

Many dumb things

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

A neuron can't think, yet minds emerge from neurons. A single person can't build a city, yet cities, languages, and whole civilisations emerge from people. Each level is made of pieces too simple to hold what they create together.
So here's the thought that's hard to shake: does the ladder stop with us? Or are we the simple pieces in something larger, the way neurons are the simple pieces in us?
Citations(2)↓
  1. 1. hachettebookgroup.com
  2. 2. en.wikipedia.org