← All workshopsRead Self-Organising Maps

Neural Networks

Move a prototype towards an observation

BOTIE

The winning prototype has already been selected. Build its update so it moves halfway towards the incoming point.
Ready to test
0 passed · 0 failed · 1 not run

An empty floor. Start with the information your machine needs.

Received result

Your answer will arrive here.

Examples, experiments and workspace controls
Live values

Connect a tool's inputs to see what it produces. You can try a branch before connecting it to Result.

Try your own inputs

Use a copy of the example to try your own data. Keep the problem's assumptions in mind, and predict the effect of a change before checking the output. You can also add another branch to compare two ways of doing the calculation.

Start at an output arrow, then click or drag to an input. Drag empty space to pan. Delete removes a selection. Ctrl/Cmd+Z undoes a change.
Context for this challenge

The winning prototype has already been selected. Build its update so it moves halfway towards the incoming point.

Botie's closest prototype has already been selected. Its next position should move towards the observation while retaining some of its old position.

Find the displacement from prototype to point, scale that displacement by one half, and add it to the prototype.

Examples and results
Winning prototype
  1. 00
  2. 12
Incoming point
  1. 04
  2. 16
Required result
  1. 02
  2. 14
Try a fresh construction

This clears this draft, including its undo history. Earlier successful attempts stay recorded. Build again without opening hints to record an independent attempt.

Stuck? Inspect a worked construction

The tools below form one possible solution. You can assemble it, follow its signals, and undo that change to return to your own construction.

Assumptions and test precision

This is a small construction problem. The lesson explains the assumptions and the parts of the full method that this example leaves out. Numerical tests allow a difference of 0.001. Lists and structures must also have the right shape.

The winning prototype crosses toward a distant point

This check uses the pieces from “Move the selected prototype halfway”.

BOTIE

The winning prototype and incoming point lie on opposite sides of the origin. Move this prototype halfway toward the point and return its new coordinates. Winner selection is already supplied.
Winning prototype
  1. 02
  2. 1-4
Incoming point
  1. 0-2
  2. 14

Use a number, text, or an array matching the requested result. For a matrix, put each row in brackets. Saving your prediction runs your current construction on these inputs and checks the earlier examples too.

Build a construction in the workspace above first. This case will test those pieces.

Which additional update would be needed to make nearby map units respond together?

The neighbourhood update gives a self-organising map its spatial organisation; this construction isolates the winner.

This is a small construction problem. The lesson explains the assumptions and the parts of the full method that this example leaves out.

Work through the Python challenges →
Continue the courseHebbian Principal Components →
← Restricted Boltzmann Machines