-
Launch 8
Machine learning model that can sort images
-
Lecture1.1
-
Lecture1.2
-
Lecture1.3
-
Lecture1.4
-
Lecture1.5
-
Lecture1.6
-
Quiz1.1
-
Lecture1.7
-
-
Natural Language Processing 7
Machine learning model that can recognise natural language commands
-
Lecture2.1
-
Lecture2.2
-
Lecture2.3
-
Lecture2.4
-
Lecture2.5
-
Quiz2.1
-
Lecture2.6
-
-
Recommendation Systems 6
Machine learning model that can recommend the reading age of a book based on data about the book
-
Lecture3.1
-
Lecture3.2
-
Lecture3.3
-
Lecture3.4
-
Lecture3.5
-
Quiz3.1
-
-
Decisions and Ethics 4
Presentation or report summarising key points
-
Lecture4.1
-
Lecture4.2
-
Lecture4.3
-
Lecture4.4
-
-
Machine Learning Algorithms 12
In this session we will be looking at some of the algorithms that make machine learning possible.
-
Lecture5.1
-
Lecture5.2
-
Lecture5.3
-
Lecture5.4
-
Lecture5.5
-
Lecture5.6
-
Lecture5.7
-
Lecture5.8
-
Lecture5.9
-
Lecture5.10
-
Lecture5.11
-
Lecture5.12
-
-
(Optional) Python and Orange 3
Data visualiastions using Orange Python code for importing data and running machine learning algorithms (decision trees and kNN)
-
Lecture6.1
-
Lecture6.2
-
Lecture6.3
-
Test and improve your model
It’s time to test your model with examples that you haven’t shown the computer before.
- If your original example for training was “What an idiot”
- Try testing the model with “You are an idiot” or “I think you are an idiot”
Try new instructions and note down the result – did the model correctly carry out your instructions? Why? Why not?
Test instruction | Outcome | Correct Y/N?
This contact form is available only for logged in users.
If you’re not happy with how the computer recognises the instructions, add some more examples. Make sure you run ‘Train new model’ with the new examples though!
Leave Scratch open and go back to the Learn & Test page in the Training tool. Type a message into the Test box that has nothing to do with kind or mean messages.
The confidence score should be very low. The computer is telling you that it’s not certain it understands your command, because what you typed doesn’t look like what it learned from your examples.
Ideas and Extensions
Instead of just kind and mean messages, can you add another category?
Is 75% the right threshold to use to decide whether the computer has recognised the command?
Experiment with different values until you have a value that works well for your machine learning model.
If you choose a number that is too high, the computer will say “Sorry I’m not sure what you mean” too often. If you choose a number that is too low, the computer will get too many decisions wrong.