Module 1 - Lesson 4: Bias in, bias out

Learners will explore how bias can appear in machine learning models due to the data used to train them. They will create their own machine learning model to classify images of apples and tomatoes, and discover how a limited dataset can lead to biased and inaccurate predictions. Finally, they will investigate two types of bias that can appear in training data.

Ishodi učenja

  • Describe the impact of data on the accuracy of a machine learning (ML) model
  • Explain the need for both training and test data
  • Explain how bias can influence the predictions generated by an ML model

Ključni pojmovi

Training data, Test data, Accuracy, Bias, Data bias, Societal bias

Struktura nastavne jedinice

  • Data types for classification
  • Supermarket AI application
  • Bias
  • Optional: Your future career

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.