Data is the experience on the AI Learning track. The training set is the only experience the model gets. Missing situations in the data stay missing in the behavior. More parameters do not invent situations you never showed.
This lesson assumes you already worked through The learning problem.
The idea in practice
List the situations that must be in the data: rare classes, new regions, bad inputs. Count them. A class with twenty examples cannot support a confident claim.
A concrete check
goal = {
'track': 'AI Learning',
'lesson': 'Data is the experience',
}
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
Assuming the spreadsheet 'covers production' without checking dates, regions, and failures. 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
Audit one dataset idea: what situation is absent?
Self-check
- Say Data is the experience 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.