← All workshopsRead Restricted Boltzmann Machines

Neural Networks

Pass a pattern through hidden units

BOTIE

Activate a hidden bit when its probability exceeds its supplied uniform draw.
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

Activate a hidden bit when its probability exceeds its supplied uniform draw.

We want hidden units to capture relationships among the visible parts of a pattern. Let's turn the visible state into hidden probabilities, sample a hidden state, and use it to reconstruct visible probabilities. This follows the two directions used when learning such a model.

Inspect the component calculation
Strict threshold(
  Value: Sigmoid(
    Score: Matrix times vector(
      Rows of coefficients: Hidden-by-visible weights
      Input vector: Visible state
    )
  )
  Threshold: Uniform draws
)
Examples and results
Hidden-by-visible weights
1-1
0.50.5
Visible state
  1. 01
  2. 10
Uniform draws
  1. 00.2
  2. 10.8
Required result
  1. 01
  2. 10
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.

Three visible bits share two hidden units

This check uses the pieces from “Sample hidden bits before reconstructing the visible pattern”.

BOTIE

Use the two hidden-by-visible weight rows and the supplied uniform draws to sample hidden bits, then return reconstructed visible probabilities. There are no biases in this example.
Visible state
  1. 01
  2. 10
  3. 21
Hidden-by-visible weights
1-10
011
Uniform draws
  1. 00.9
  2. 10.1

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.

Where does randomness enter this pass, and which values remain probabilities at the output?

A reconstruction pass supplies part of an RBM procedure; learning additionally compares data and model statistics.

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 courseSelf-Organising Maps →
← Hopfield Networks