Skip to content
PlayOwl

Computers & Digital Literacy · Grade 9

Rules-Based and Learned Models

Learners build three simple models entirely by hand on small fictional datasets: a one-feature threshold learned by counting the errors of each candidate cutoff, a two-level decision tree grown by choosing the split with the fewest errors, and a k-nearest-neighbors classifier using Euclidean distance and a majority vote. They then compare hand-written rules with learned models on transparency, maintenance, adaptability and data needs.

  • 4 lessons
  • About 110 minutes
  • Models by hand check: 9 questions
  • Ways to answer: fill in the blanks, choose an answer, trace code, match pairs, type a number and sort into groups
Try it now (no account) One of the five free starter courses Open in PlayOwl

What learners will discover

  • Contrast a hand-written rule with a learned rule, and learn a one-feature threshold by counting false alarms and misses for each candidate cutoff.
  • Grow and apply a two-level decision tree by hand, choosing each split by the number of misclassifications it leaves.
  • Classify a new example with k-nearest neighbors using Euclidean distance and a majority vote, and explain how the choice of k changes the result.
  • Compare rule-based and learned approaches on transparency, maintenance, adaptability and data needs, and recommend one (or a combination) for a scenario.

Lessons

  1. Hand-written rules and learned thresholds 7 steps4 practiceabout 30 min
  2. Decision trees by hand 6 steps4 practiceabout 28 min
  3. k-nearest neighbors 6 steps4 practiceabout 28 min
  4. Rules or learning? 6 steps3 practiceabout 24 min
  5. Models by hand check 9 questions at the end

Keep exploring

More 9th grade computer skills

Guide for grown-ups