Robots and Physical Computing

Artificial Intelligence often feels like "magic" happening inside a powerful computer. But at its core, a neural network is just a series of mathematical decisions. In my previous posts, we looked at how to simulate these decisions in Python. Today, we are taking that "brain" out of the computer and building it in the real world using three BBC micro:bits . In this project, each micro:bit acts as a single neuron . By wiring them together, we create a physical network capable of logic and decision-making. The Math: How a Neuron "Thinks" Every neuron in our network follows a simple linear formula to decide whether or not to "fire" (send a signal): Figure 1 - the maths If the result Net  >=0  the neuron fires (Output = 1). If it’s less than 0, it stays at Output = 0. Step 1: The Logic Gate "Cheat Sheet" Before we flash the code, we need to decide what we want our neurons to do. By changing the weights and bias , we can turn a micro:bit...

Artificial Intelligence (AI) is everywhere—recommending videos, recognising faces, and even helping cars drive themselves. But what actually powers these systems? At the heart of many AI systems is something called a neural network . And here’s the exciting part: you don’t need a supercomputer to explore one. 👉 In this challenge, you’ll build a working neural network using micro:bits —and see how AI works from the inside. 🔍 What Is a Neural Network? A neural network is a system made of connected “neurons” that pass information to each other. It’s usually organised into layers: Input layer → receives data Hidden layer → processes information Output layer → produces a result One important detail: the input layer doesn’t actually process anything —it just passes signals forward. If you want a deeper explanation, this post breaks it down clearly: 👉 https://robotsandphysicalcomputing.blogspot.com/2021/02/explaining-tinkercad-microbit-neural.html ⚡ Make It Physical with micro:bits Inst...

From Motion to Meaning: Detect your nose in Scratch 3 When I first wrote about Scratch and Webcams back in 2019, the excitement was centred on the "New Frontier" of Scratch 3.0. We were exploring how to bring back the classic video sensing features—making cats jump or bubbles burst when we waved our hands. At the time, that was the peak of "Magic" in the classroom: the physical world interacting with the digital one. Fast forward to today, and the landscape for STEM educators and makers has shifted. We are no longer satisfied with the computer merely knowing that something moved; we want the computer to know what is moving  We have moved from simple motion detection to Artificial Intelligence and Computer Vision. If you want to re-energize your STEM lab or maker space, it’s time to move beyond the basic Video Sensing blocks and dive into the Face Sensing extension, So here is an example project playing with htese ideas. The Project: The Nose-Tracking Security ...

From "Hello" to "Bonjour": Bringing AI to Life  I recently revisited one of my favourite projects based around using  Machine Learning for Kids  and  Scratch 3 , and the result was surprisingly elegant. For STEM educators and makers, this is more than just a coding trick; it’s a gateway to AI literacy and global communication.    It started with a simple question: Could I make a computer not just hear me, but understand my intent across languages?  I’m always looking for that "Aha!" moment—the point where the complexity of high-level tech melts away into a simple, working project - and is cool. The end goal has changed since the original project  from getting it to just saying a prescribed phrase to translating typed-in phrases when it hears "French" - it is even cooler than before. The Journey: Making the Connection I sat down with the goal of creating a "Polyglot Sprite." The setup through the Machine Learning for Kids Scratch templ...

Question: How easy is it produce a comic/cartoon using genetative AI? Let's start with  using ChatGPT4o to produce cartoons. The idea was inspired by a tweet by Dr Thomas Lancaster see below First, use a simple prompt to prime the system and generate the main panels. ChatGPT can now generate multiple images in a row. I asked for 8 panels. (2/6)  pic.twitter.com/wqz2DyAUFe — Thomas Lancaster (@DrLancaster)  June 17, 2024 Slightly modifying the prompts it is possible to get it to create the images and combine them in a GIF. I have split the two task into two prompts  The first prompt applies some principles of prompt engineering Persona: In this case two the persona of the writer " You are an experienced comic book designer and a witty writer " and who it is for " Computing student in Higher Education in the UK " Task: Creating a guide that educational and entertaining, but with minimal textual output. Action: The details a comic with 8 panels of consistent style,...