MARK I PERCEPTRON · 1958 SIMULATION
Starter mission: choose AND and click Train Burst (5).
Decision space
Dots are examples. The dark line is the model. Red rings reveal its current mistakes.
- Square = class 0
- Circle = class 1
- Ring = current mistake
Test one dot
Set a coordinate and ask the trained model which class it predicts.
X1 1.0
X2 0.0
- GUESS SCORE: 0.20
- OUTPUT: 1
- LINE CUT POINT: 0.20
- CASE STATUS: AND: WORKING CASE
ACCURACY 0%
Accuracy = examples sorted correctly out of 4.
Read the decision
Weights amplify the inputs. Bias nudges the starting position. Together they decide which side of the line a dot lands on.
z = w₁x₁ + w₂x₂ + b. If z ≥ 0, output 1; otherwise output 0.
A hidden layer combines multiple boundaries, creating regions a single straight line cannot represent.
How the learning rule works
w ← w + η × error × x
Every wrong guess adjusts the weights. Correct guesses leave the line alone.
1958 hardware vs. modern training
The 1958 mode adds mild channel noise and slower feedback. The 2012 mode is faster and cleaner—but this model still has only one boundary.
OPEN LAB LOG + DIAGNOSTICS
Inspect every prediction, error, and training round.
- DATASET ACCURACY: 0 / 4
- ROUNDS TRAINED: 0
- ONE-LINE CHECK: VISUAL CHECK
| x1 | x2 | target | pred | error |
|---|
Can you beat XOR?
Its matching classes sit on opposite corners. Rotate and slide one line however you like—there will always be a mistake.
Two lines beat XOR
One straight boundary can't split XOR. Two can — if you combine them the right way. This is what a hidden layer buys you.
- Hidden unit A learns OR — the dashed teal line. It fires (1) for every point except (0,0).
- Hidden unit B learns NAND — the dashed amber line. It fires (1) for every point except (1,1).
- Output unit fires only when both hidden units fire — A AND B. That overlap is exactly the two XOR corners that should be class 1.