Mr. Scandrett's ClassroomOS

AI ORIGINS · LESSON 06

Make One Line Learn the Pattern

Starter mission: can one straight line learn to sort the dots?

IBM 704 / MARK I PERCEPTRON / ROSENBLATT DEMONSTRATION MODE

Starter mission: choose AND and click Train Burst (5).

1. Pick a pattern

2. Train the line

Best first run: AND, then Reset, then Train Burst (5).

Geometry View

This is the heart of the lesson: dots are examples, the line is the model, and glowing rings mark mistakes.

  • Square = class 0
  • Circle = class 1
  • Ring = current mistake

Try One Dot

Move the sliders to test one input point, then press Run Prediction.

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 means how many of the 4 dots the line gets right.

OPEN LAB LOG + DIAGNOSTICS

Use this section when you want the full logbook view of predictions, errors, and training rounds.

  • DATASET ACCURACY: 0 / 4
  • ROUNDS TRAINED: 0
  • ONE-LINE CHECK: VISUAL CHECK
LAB LOGBOOK
x1 x2 target pred error

Limit Notes

WHAT THIS IS

A perceptron is a small guess machine. It learns by moving one straight line.

WHAT IT CAN'T DO

XOR cannot be solved by one line in two dimensions. This is a structural limit, not just undertraining.

HOW TO USE IT LIKE IT'S 1958

  • Set channels to (1,0). Run.
  • Try 0.1 learning rate first. Watch what changes.
  • Adjust W1 upward until output flips.
  • Switch to XOR. Can you draw one line that separates all points? Try.

History Panel: Mark I Perceptron (1958)

The specific machine demonstrated in 1958 was the Mark I Perceptron.

Machine Context

  • ScientistFrank Rosenblatt
  • InstitutionCornell University
  • Hardware ContextImplemented on an IBM 704 computer
  • Physical MachineMark I Perceptron

Perceptron is the model. Mark I Perceptron was the physical machine.

Where It Sits on the Timeline

  1. Turing proposes the imitation game
  2. Mark I Perceptron is demonstrated
  3. ELIZA demonstrates scripted NLP conversation
  4. Expert systems expand symbolic AI
  5. Deep learning breakthroughs revive neural methods at scale

Lesson Outputs

Each team should publish a short reflection and demo link at the end of class.

Starter Kit Perceptron Lab live starter workspace Use the built-in Mark I Perceptron emulator on this page Extension Implement a two-layer XOR solver and compare traces Optional challenge for advanced students Navigate Back to STEAM Lessons Return to the full ClassroomOS lesson shelf