Module 2 - Lesson 4: Solving problems with ML models (part 2)

In this lesson, learners will continue to apply the AI project lifecycle. They will begin to train a machine learning model to solve a problem of their choice and test it. They will examine the relationship between confidence scores, confidence thresholds, and accuracy in machine learning model predictions. Finally, they will measure the accuracy of their machine learning (ML) models.

Ishodi učenja

  • Apply the ‘training’ and ‘testing’ stages to a real machine learning project
  • Describe what a confidence threshold is and why they are used
  • Demonstrate how the accuracy of a ML model is measured

Ključni pojmovi

Confidence score, Confidence threshold, Accuracy

Struktura nastavne jedinice

  • Activity 1: Stages of the project lifecycle
  • Activity 2: Train your model
  • Activity 3: Confidence thresholds and accuracy
  • Activity 4: Test your model
  • Optional: Worked examples

Preuzmite materijale za nastavnu jedinicu

Za preuzimanje scenarija poučavanja, prvo se prijavite ili registrirajte za besplatni Raspberry Pi Foundation račun.
Postavit ćemo vam nekoliko pitanja kako bismo razumjeli kako ćete upotrebljavati materijale.