Aisle 3No. 31 of 460
Splashery
Multilayer Net
439,988 small parts. Assembled in your browser.
Empty. Now look down.
Swipe across the pack to tear it open.
Press and hold. It pulls itself together.
Let go to drop it.
It stays in its pack here. The Playground has the rest.
AI and Computing · Built from a recipe
Multilayer Net
One perceptron can only split its inputs with a single straight line, so it cannot learn XOR, “exclusive or”, which is 1 when exactly one of two inputs is 1.
Play with it in the Playground
How to play
Tap it to try all four inputs. Hands-on: tap each input to flip it; XOR answers.
Toy facts
- Item
- No. 31 of 460
- Shelf
- Aisle 3, AI and Computing
- Kind
- Built from a recipe
- Small parts
- 439,988
- Sound
- Yes
- Hands-on
- Yes
- Batteries
- None
- Assembly
- It does that itself
- Licenses
- Own work (made in the page)
- Price
- $0.00
Small parts are the splats in its usual build on a computer. A phone may draw fewer.
Its controls
| Control | Kind | Range | Start |
|---|---|---|---|
| Try all four inputs | Tap | ||
| Run | Button | ||
| Flip | Button | ||
| View | List | 2 choices | Poster (2D) |
About it
One perceptron can only split its inputs with a single straight line, so it cannot learn XOR, “exclusive or”, which is 1 when exactly one of two inputs is 1. Put neurons in layers and it can. Here an OR neuron and a NAND (“not both”) neuron feed an AND neuron, and together they give XOR. Blue wires add to a neuron's sum and red wires subtract.
Tap it and it tries the inputs 00, 01, 10 and 11 in turn, lighting each neuron that fires, and fills in the truth table: 0, 1, 1, 0. Pick the poster or a 3D model in the Splash tab. With ✋ Hands-on on, tap each input lamp to flip it: the OR and NAND neurons and the output show XOR's answer at once, and the truth table marks the row.
Details
- Splats
- Opens at 200,000 at Mid Detail, 120,001 at Low, and up to 630,000 at Max
Is it right?
The hidden units produce the XOR truth table correctly. The splash demonstrates a fixed nonlinear circuit; it does not learn XOR from examples.
Correct
A single linear decision boundary cannot represent XOR; hidden nonlinear units can.1
The fixed hidden units compute OR and NAND; their final threshold computes XOR for all four input pairs.
Correct
The XOR output is one when exactly one input is one.2
The actual XOR helper returns 0, 1, 1, 0 for 00, 01, 10, 11.
Simplified
The picture illustrates a multilayer network, not a trained model.1
The weights and thresholds are stored constants; tapping cycles the four input cases.
- 1Multilayer perceptrons, Dive into Deep Learning authors
- 2Half adder, All About Circuits textbook
- Simplified
- The XOR network uses fixed threshold units. Its truth table is real, but there is no loss calculation or training step.
Sources and credits
Made in Splashery. Its code is MIT.
