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?
7 / 41
BackNext

Strength, not just presence

So far, every signal has counted the same. One input, one vote. But that is not how real thinking works. Some signals matter more than others.

One quick note on words. From here on, when we say "neuron" we mean the artificial kind, the simple math version we are building, not the brain cell. When we mean the real thing, we will say "brain cell" or "biological neuron."

Look at the wires connecting the inputs to the central neuron. Each wire now has a weight, a number between 0 and 1. The weight controls how much of that signal gets through. A weight of 0.8 lets most of it pass. A weight of 0.1 barely lets anything through.

So the neuron stops simply counting its inputs. Instead, it gives each one its weight, and adds up what's left.

A signal with a high weight contributes a lot. A signal with a low weight barely registers. That is how the neuron decides what matters.

Click the inputs on or off, and drag the weight labels to watch the total change.

The signals are the same. What changed is the connections.

Citations(2)↓
  1. 1. doi.org
  2. 2. deeplearningbook.org
Citations(2)↓
  1. 1. doi.org
  2. 2. deeplearningbook.org