In this post, I want to share a Scratch extension that I’ve been working on today: enabling access to books data from the OpenLibrary API through new Scratch blocks.
Most of the work I do on Machine Learning for Kids involves adding machine learning models into Scratch. To enable students to create interesting projects, it also helps to make it easier to get external data into Scratch that they can use for training and classifying. A few examples of where I’ve done this in the past include creating Scratch blocks to access weather data, data from Spotify, and data from Wikipedia.
New blocks
The new blocks I’ve worked on today use the OpenLibrary API to enable access to information about books.
Extensions in Scratch let you add additional blocks to the palette. I’ve written about how to create extensions before, but in this post I want to share my latest extension which adds MQTT support.
I don’t have a particular Scratch project in mind for this yet, but publishing and subscribing to an MQTT broker from a Scratch project would allow multiple web browsers each running Scratch to communicate with each other. I’m sure there are some fun things this could be used for.
One of the conference presentations I gave last year was a talk at Heapcon, sharing some stories of AI/ML lessons I’ve run in schools. The focus of the talk was how I’ve seen children understand and react to machine learning technologies.
I’ve since expanded the ideas in this talk into a mini-book at MachineLearningForKids.co.uk/stories but here is a recording of where some of these stories started.
In this post, I want to share an example of Scratch projects that use live weather data.
At the Raspberry Pi Clubs Conference last week, I talked about the idea of Scratch projects that use live data: projects that do something different every time you run them, based on when or where they are run.
I love this idea. It’s something I’ve talked about many times – like when I tried bringing NASA data into Scratch, or when I built Scratch extensions for different web APIs, such as Wikipedia, Twitter, and Spotify.
I think doing this brings a new perspective to Scratch. Live data can bring projects to life.
So I thought I’d share another example: this time, weather data from Open Meteo.
This workshop is a step-by-step guide for how to create a Scratch extension.
I created it for educators and coding group volunteers, who would like to customize Scratch for their students by giving them new and unique blocks to create with. In particular, I wanted to make this accessible to people who perhaps don’t necessarily think of themselves as developers and wouldn’t otherwise know how to clone the Scratch Team repos and start hacking it.
I’ve wrapped all the complicated bits in scripts that set everything up, and prepared an online Scratch extension development environment – so everything can be done in a web browser without having to install or configure anything on your own computer.
I’ve included step-by-step instructions for building different types of Scratch extensions, including Scratch blocks based on web APIs, and Scratch blocks based on JavaScript modules from npm.
This post was written for MachineLearningForKids.co.uk/stories: a series of stories I wrote to describe student experiences of artificial intelligence and machine learning, that I’ve seen from time I spend volunteering in schools and code clubs.
Some of the best lessons I’ve run have been where a machine learning model did the “wrong” thing. Students learn a lot from seeing an example of machine learning not doing what we want.
Perhaps my favourite example of when something went wrong was a lesson that I did on Rock, Paper, Scissors.
Students make a Scratch project to play Rock, Paper, Scissors. They use their webcam to collect example photos of their hands making the shapes of rock (fist), paper (flat hand), and scissors (two fingers) – and use those photos to train a machine learning model to recognise their hand shapes.
It this particular lesson, the project worked really nicely for nearly all the students. There was one student where things went a little bit wrong.
This post was written for MachineLearningForKids.co.uk/stories: a series of stories I wrote to describe student experiences of artificial intelligence and machine learning, that I’ve seen from time I spend volunteering in schools and code clubs.
Machine learning models don’t just give an answer, they also typically return a score showing how confident the system is that it has correctly recognized the input.
Knowing how to use this confidence score is an important part of using machine learning.
An example of how a student used this in their project is shown in this video. Their Scratch script says that if the machine learning model has less than 50% confidence that it has correctly recognized a command, it replies “I’m sorry I don’t understand” (instead of taking an action).
The project was trained to understand commands to turn on a lamp or a fan. When they asked it to “Make me a cheese sandwich”, their assistant didn’t try to turn the lamp or fan on, it said “I don’t understand”
This command was unlike any of the example commands that had been used to train the model, causing the machine learning model to have a very low level of confidence that it had recognised the command. This was represented with a very low confidence score.
The challenge for the students making this project was knowing what confidence score threshold to use. Instead of telling them a good value to use, I let them try out different values and decide for themselves. By playing and experimenting with it, they get a feel for the impact that this threshold has on their project.
