Ordering the examples on the AI Learning track. Curriculum learning shows easier or cleaner examples first, then harder ones. It can stabilize training. It can also hide the hard cases until too late if you never reach them.
This lesson assumes you already worked through Learning from people.
The idea in practice
Define easy with a rule, not a feeling. Schedule a point where hard examples are the majority. Check that the rare class still appears.
A concrete check
goal = {
'track': 'AI Learning',
'lesson': 'Ordering the examples',
}
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
A curriculum that drops all the failure cases 'until the model is ready' and never adds them. 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
Define easy and hard for a speech model in one sentence each.
Self-check
- Say Ordering the examples 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.