AI / ML & Autonomy

Features, Labels and Training Data

Discover what features and labels are, how training examples teach a model, and why data quality — not just algorithm choice — determines whether a classifier is trustworthy.

High school
Time estimate
30–35 min
Complexity
advanced
Maturity
pilot ready
Simulator readiness
implemented
Software available now
Implemented as interactive feature/label explorer at `/twin/learn/activities/aiml_assisted_classification` — teaching-grade; no real ML training pipeline, no external AI API.

Learning outcomes

Student can define feature and label, select useful features from telemetry, assign a correct label to a given example, and explain how a biased dataset degrades classifier performance.

  • Define feature and label in a machine learning context.
  • Select at least three useful features from a telemetry vector and justify each.
  • Explain how data bias or missing examples degrades classifier performance.

Concept primer

Discover what features and labels are, how training examples teach a model, and why data quality — not just algorithm choice — determines whether a classifier is trustworthy.

Open Features, Labels and Training Data at `/twin/learn/activities/aiml_assisted_classification` — interactive feature selection, label assignment, and data quality feedback (teaching-grade; no real ML training pipeline).

Label five telemetry windows as nominal / warning / fault candidate; list one feature that most influenced each label decision.

Interactive lab

Teaching-grade software activity slot — not a flight simulator or certified propagator.

Step 1 — Choose a telemetry example

Telemetry Examples

Each row is one telemetry snapshot. Select an example to label.

FeatureValueSelected?
Battery Voltage7.4 V
OBC Temperature43 °C
Attitude Error0.25°
Data Backlog8 MB
Packet Age2 s

3 features selected. Select at least 3 for a meaningful model input.

Step 2 — Assign a label

Label Assignment

Based on the features you selected, what class does this example belong to?

Self-check · Local only

3 questions — 0/3 answered correctly

Local-only. No submission, no grade. Answers revealed here only.

What is a 'feature' in a machine learning context?

What does a 'label' tell a machine learning model?

Why does a biased training dataset harm a fault classifier?

Evidence capture · Local only

Your evidence — Features, Labels & Training Data

Local-only. No submission, no backend, no grade. Copy or screenshot to share.

Example selected
Nominal orbit pass
Features selected
voltage, pointing_error, packet_age
Label assigned
none
Correct label
nominal
Result
not yet assigned
Explanation
All fields within normal bounds. Battery healthy, temperature cool, error converged, backlog manageable, packets fresh.

Evidence capture

Expected outputs learners should be able to show after the lab (Phase 9 evidence engine preview available).

  • Selected features and justification for each choice
  • Assigned label and explanation for a given telemetry example
  • Note on one way a missing or biased feature would harm the model
  • Self-check summary and copied evidence text

Reflection

Select features from a telemetry example; assign a label (nominal / warning / fault candidate); review why each feature choice helps or hurts the model.

Responses are not persisted in this preview unless a specific activity component adds storage later.

Assessment / quick check

Name two ways a biased or incomplete training dataset could cause a fault classifier to make dangerous mistakes.

Teacher notes

Position as a data ethics conversation: what happens when training data is mostly nominal? Ask students to find a dataset gap.

Next activity

Suggested progression from the mission learning path. Links avoid missing activity routes.