-
Launch
Machine learning model that can sort images
-
Natural Language Processing
Machine learning model that can recognise natural language commands
-
Recommendation Systems
Machine learning model that can recommend the reading age of a book based on data about the book
-
Decisions and Ethics
Presentation or report summarising key points
-
Machine Learning Algorithms
In this session we will be looking at some of the algorithms that make machine learning possible.
-
(Optional) Python and Orange
Data visualiastions using Orange Python code for importing data and running machine learning algorithms (decision trees and kNN)
How do machines learn?
You want a computer to perform a complex task…
With computer programming:
- You break down the complex activity into a set of simple instructions.
- You use these instructions to tell the machine how to perform the task.
With machine learning:
- You collect a set of examples of the task being done.
- The computer learns how to do the task from the examples you give it.
The next two activities will show how this works in practice. In each case the machine is being taught to recognise images.
Activity – Quick, Draw
This is a game built with machine learning. You draw, and a neural network tries to guess what you’re drawing. When you have finished look at how your drawings were recognised and also the ‘data set’ of drawings that have been done by others.
Play the game here:
https://quickdraw.withgoogle.com/
Find out how it works here:
https://www.youtube.com/watch?v=X8v1GWzZYJ4
Activity – Teachable Machine
Teachable Machine allow you to use your webcam to capture images or upload images from your computer to train a computer model:
https://teachablemachine.withgoogle.com/train/image
Follow the tutorial to train your own model.
This link is the previous version of Teachable Machine. You can train a model to recognise different gestures using your camera live in your browser.
Play the game here:
https://teachablemachine.withgoogle.com/v1/
If your cameras are disabled watch this video to see how this works: https://www.youtube.com/watch?v=3BhkeY974Rg