a single set of data used for training or testing

a system that uses patterns in data to represent something in the real world and can be used to make predictions

createAI setup

British English CC

Bad class

Good class

Gathering data for a model

Computing

AI and machine learning applications

Training and testing a model

Improving a model

Building a data-driven application

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

a category assigned to multiple data points

What is a sample in the context of gathering data for a model?

{{ }} is measured in three directions: x (side-to-side), y (forward-backward), and z (up-down).

because computers cannot understand numerical data

so the model can predict whether a movement is good or bad based on patterns

Why do we label movement data with 'good' and 'bad'?

A {{ }} is a way of representing something in the real world using data patterns.

a system that represents real-world data patterns

a method where decisions are based on patterns in data

When creating a movement model, motion values for x, y and z are plotted against ...

a chatbot that always gives the same response

a smart thermostat that adjusts over time

The phrase ‘I know!’ appears in the Quick Draw system when enough {{ }} is provided for a high-confidence prediction.

It makes decisions based on pre-defined rules.

It improves by adapting how it finds patterns in data.

It does not require large amounts of data.

Which of the following best describes a data-driven system?

a system that processes data, finds patterns and adapts

a method where decisions are made using patterns in large data sets

a system that follows predefined instructions or conditions

a subset of AI where systems improve as they process more data

Match the AI-related term with its definition.

A TV recommendation system that uses AI to suggest shows is an example of a {{ }} approach.

to slow down processing and make decisions more carefully

to identify patterns accurately and make better predictions

Why do AI systems require large amounts of data?

Gathering data for a model

Lesson outcome