← All workshopsRead Detecting Patterns a Model Cannot Reconstruct

Anomaly Detection

Decide which reconstructed records need review

BOTIE

Calculate row-wise mean squared errors without reducing all records together.
Ready to test
0 passed · 0 failed · 2 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

Calculate row-wise mean squared errors without reducing all records together.

Botie has prepared readings, their reconstructions, and a fixed threshold.

Inspect the component calculation
Mean within each row(
  Rows of measurements: Square(
    Value or list: Subtract(
      Starting value: Prepared records
      Value to remove: Reconstructed records
    )
  )
)
Examples and results
Prepared records
13
22
Reconstructed records
11
22
Required result
  1. 02
  2. 10
Prepared records
04
33
Reconstructed records
00
00
Required result
  1. 08
  2. 19
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

Models and preprocessing must already be fitted. Alerts need investigation and are not fault diagnoses. 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.

One row is exactly at the alert threshold

This check uses the pieces from “Turn each record's reconstruction error into an alert”.

BOTIE

Botie reconstructs three two-channel sensor readings. Compute the mean squared error within each row and flag rows strictly above threshold 2. Return 1 for an alert and 0 otherwise, preserving sensor-row order.
Prepared records
02
44
11
Reconstructed records
00
22
11
Fixed error threshold
2

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 could changed feature scales alter alerts even if the reconstruction mechanism stayed fixed?

Retain preprocessing and threshold selection alongside the reconstruction model.

Models and preprocessing must already be fitted. Alerts need investigation and are not fault diagnoses.

Work through the Python challenges →
Continue the courseRecording Which Things Are Connected →
← Finding Readings That Are Easy to Separate