British English CC

Building a data-driven application

Computing

AI and machine learning applications

Gathering data for a model

Training and testing a model

Improving a model

Documenting and evaluating a machine learning model

This unit is designed to develop pupils programming skills in a new engaging context: physical computing, using the BBC micro:bit. They will get acquainted with the host of components built into the micro:bit, and write simple programs that use these components to interact with the physical world.

Machine learning using the micro:bit

Why is a smiley face a suitable icon for a "good" movement?

It checks if a prediction reaches a certain level of certainty.

What does the ```is ML detected``` block do?

The level of certainty that causes an input to match a class is called the ...

The default recognition point in CreateAI is ...

checks if a class is detected with a certain level of confidence

gives a numerical value for the model's confidence

To use your machine learning model on the micro:bit, you need to {{ }} your program to the device.

to allow the model to recognise when data doesn't fit existing categories

What is the purpose of a null class in a machine learning model?

The process of removing or replacing outliers is called ...

Which of the following is **not** a method for improving a machine learning model?

The model predicts the wrong class for the data.

What does it mean for data to be misclassified?

To reduce uncertainty in a model's predictions, you can add a {{ }} class.

Building a data-driven application

Lesson outcome