01
5 minute interactive lab

How a neuron makes a decision

How does evidence become a decision?

YOU’LL LEAVE KNOWINGA neuron is a weighted vote followed by a decision rule.
THE EXPERIMENT

Make the neuron change its mind.

Move the controls. Watch the internal state respond. The explanation follows the behavior—not the other way around.

Runs the real small-scale equationThe displayed values are calculated from the formula shown in this lesson.
INPUTSChange the evidence
0.90 × +0.550.68 × +0.350.30 × −0.45bias −0.35
sigmoid89%SHIP
weighted evidence+0.25
THE MENTAL MODEL

A neuron is a weighted vote followed by a decision rule.

Each input contributes evidence. Its weight says how strongly—and in which direction—it matters. The bias sets the default tendency; the activation turns the final score into a usable output.

IN DEVELOPER TERMSoutput = activate(inputs · weights + bias)
GO DEEPER

Check the model against the source.

Connectionism optimizes for intuition, then points you to the rigorous treatment.

  1. Michael NielsenUsing neural nets to recognize handwritten digits
  2. Stanford CS231nNeural Networks Part 1
NEXT CONNECTION

Why can’t one neuron solve every pattern?

Why neural networks need hidden layers

Continue to lab 02