Training and testing a model
Lesson details
Learning outcome
I can train a machine learning model and test the model’s predictions.
Key learning points
- A classifier's predictions are only as accurate as their training data allows.
- Classifiers can still make predictions with a high confidence score, even if the training data is poor.
- Causes of poor training data include: outliers, limited training data and poorly labelled data.
- It is important to test a classifier to make sure the outputs are as expected.
Keywords
Training data - a set of examples used to teach a machine learning model how to recognise patterns
Prediction - the output that a model generates based on the patterns determined from the training data
Confidence - a measure of how likely the output of a model is correct
Bias - to disproportionately favour one side, group, or outcome over others
Outlier - a data point that significantly differs from the rest of the data in a data set
Common misconception
More training makes a perfect model.
Not neccessarily - models can become too specialised and fail on new data.
Teacher tip
It is important to point out to pupils that classifiers can still make predictions with a high confidence score even if the training data is poor.
Equipment
Pupils will need access to a physical device to capture data and a means of creating a data-driven application. Examples in this lesson use micro:bits and CreateAI https://oak.link/createai
File needed for this lesson
microbit-Oak 1.29 MB (HEX)
Download this file to use in the lesson.
Licence
Lesson video
Loading...
Prior knowledge starter quiz
6 Questions
Q1.Why is it important to hold the micro:bit in the same position when recording movement samples?
Q2.A approach involves using patterns in data rather than predefined rules.
Q3.Which axis changes the most when moving a device side to side?
Q4.A is a collection of similar data samples grouped together under a label.
Q5.A data-driven system requires a large number of to learn patterns.
Q6.Why do we need to collect multiple samples for a model?
Assessment exit quiz
6 Questions
Q1.What is training data in machine learning?
Q2.A classifier uses in a model to predict which class new data belongs to.
Q3.What is an outlier in a data set?
Q4.What is a classifier in machine learning?
Q5.Match the term with its definition.
a model that sorts data into categories
a set of examples used to teach an AI model
the model's output based on recognised patterns
a data point that differs significantly from the rest
Q6.Why is it important to test a model with different people?
To help you plan your 9 computing lesson on: Training and testing a model, download all teaching resources for free and adapt to suit your pupils' needs...
To help you plan your 9 computing lesson on: Training and testing a model, download all teaching resources for free and adapt to suit your pupils' needs.
The starter quiz will activate and check your pupils' prior knowledge, with versions available both with and without answers in PDF format.
We use learning cycles to break down learning into key concepts or ideas linked to the learning outcome. Each learning cycle features explanations with checks for understanding and practice tasks with feedback. All of this is found in our slide decks, ready for you to download and edit. The practice tasks are also available as printable worksheets and some lessons have additional materials with extra material you might need for teaching the lesson.
The assessment exit quiz will test your pupils' understanding of the key learning points.
Our video is a tool for planning, showing how other teachers might teach the lesson, offering helpful tips, modelled explanations and inspiration for your own delivery in the classroom. Plus, you can set it as homework or revision for pupils and keep their learning on track by sharing an online pupil version of this lesson.
Explore more key stage 3 computing lessons from the Machine learning using the micro:bit unit, dive into the full secondary computing curriculum, or learn more about lesson planning.