← All workshopsRead Finite Scalar Quantisation

Natural Language Processing

Snap each coordinate to a level

BOTIE

Return each original coordinate minus its rounded coordinate.
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

Return each original coordinate minus its rounded coordinate.

A learned codebook is not the only way to restrict a representation. We can specify a fixed grid of allowed coordinate values. Let's round an already-bounded vector onto that grid and measure the reconstruction error caused by the rounding.

Inspect the component calculation
Subtract(
  Starting value: Bounded coordinates
  Value to remove: Round to a level(
    Values: Bounded coordinates
  )
)
Examples and results
Bounded coordinates
  1. 0-0.7
  2. 10.2
  3. 20.8
Required result
  1. 00.3
  2. 10.2
  3. 2-0.2
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.

Your last tested pieces can start the full construction. An existing draft there keeps its own pieces.

Coordinates land exactly halfway between levels

This check uses the pieces from “Round coordinates and account for the lost detail”.

BOTIE

Round each supplied bounded coordinate to an integer, using the workshop's tie rule toward positive infinity. Return the total squared reconstruction error, including both halfway cases.
Bounded coordinates
  1. 0-0.5
  2. 10.5
  3. 21.25

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.

How does selecting levels independently differ from choosing one complete codebook vector?

The reconstruction set defines what a quantiser can express; bounding inputs is an additional stage omitted here.

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 courseA Vector for a Word →
← Codebook Quantisation