← All workshopsRead Dropout

Neural Networks

Keep the average signal steady

BOTIE

The supplied mask contains 1 for surviving activations and 0 for dropped activations. Build inverted dropout using a keep probability of one half.
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 supplied mask contains 1 for surviving activations and 0 for dropped activations. Build inverted dropout using a keep probability of one half.

A sampled mask removes some of Botie's activations during training. The survivors need scaling so their expected contributions remain comparable across masks.

Multiply activations by their mask entries, then divide surviving values by the keep probability.

Examples and results
Activations
  1. 02
  2. 14
  3. 26
Sampled mask
  1. 01
  2. 10
  3. 21
Required result
  1. 04
  2. 10
  3. 212
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.

A negative activation survives the sampled mask

This check uses the pieces from “Apply a mask with a one-half keep probability”.

BOTIE

Apply the supplied dropout mask with a keep probability of one half. Return the scaled activations. This operation does not include a ReLU, so surviving negative values must remain negative.
Activations
  1. 0-2
  2. 10
  3. 25
  4. 33
Sampled mask
  1. 01
  2. 11
  3. 20
  4. 31

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 should activations be treated at inference after training with inverted dropout?

At inference the activations pass through without this masking or scaling.

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 courseNormalisation Layers →
← Training a Small Network