Representations on the AI Learning track. A representation is how you turn raw input into numbers or tokens. Text becomes tokens. Categories become indexes. A bad representation throws away the signal or invents order that is not real.
This lesson assumes you already worked through Features the model can use.
The idea in practice
Do not encode colors as 1, 2, 3 unless distance means something. For categories without order, use a one-hot or an embedding. Keep a map from index back to the name.
A concrete check
goal = {
'track': 'AI Learning',
'lesson': 'Representations',
}
checks = [
'input available at decision time',
'score matches the real decision',
'failure case written down',
]
print(goal['lesson'])
for item in checks:
print('-', item)
Run the sketch locally if you have Python. The printout is a reminder of the checks, not a trained model. Replace the strings with the real inputs from your own example before you treat it as a design.
What usually goes wrong
Sorting category names alphabetically and treating the integer as a magnitude. When this happens, stop adding parameters or tools. Fix the check, the data, or the permission, then run the same example again.
What to write down
- The input you are allowed to use at decision time.
- The output and the score or pass rule.
- One failure you will test on purpose.
- What you will not claim the system can do.
Practice
Pick three raw fields and write the representation you would store for each.
Self-check
- Say Representations in one sentence that mentions an input and an output.
- Name the failure mode in this lesson and the check that would catch it.
Done when: you can explain this lesson without the page open, and you have a written failure case.