Designing a loss on the How to Make AI Models track. Sometimes you combine losses: prediction plus a penalty for a constraint. Weight them so one term does not drown the other. Log each term.
This lesson assumes you already worked through A custom layer.
The idea in practice
Start with one loss. Add a second only when the first cannot express the constraint.
A concrete check
goal = {
'track': 'How to Make AI Models',
'lesson': 'Designing a loss',
}
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 weighted sum you never inspect, dominated by one term. 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
Write two loss terms and how you would know one dominates.
Self-check
- Say Designing a loss 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.