Train a baseline before a fancy model on the How to Train Models track. A baseline is a majority class, a mean, or a linear model. Training a deep model first wastes days and gives you nothing to beat.
This lesson assumes you already worked through Preprocessing that fits on train only.
The idea in practice
Score the baseline on the frozen validation set. Record it. Only then try a richer model.
A concrete check
goal = {
'track': 'How to Train Models',
'lesson': 'Train a baseline before a fancy model',
}
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
Skipping the baseline and declaring a network successful. 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
Implement the baseline in words: what it predicts for every row.
Self-check
- Say Train a baseline before a fancy model 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.