The forward pass on the How to Make AI Models track. The forward pass computes the output from inputs with no updates. You should be able to call it on one batch and see the output shape before you train.
This lesson assumes you already worked through Shapes and broadcasting.
The idea in practice
Run one batch in eval and train mode. See what changes. Then turn on the loss.
A concrete check
goal = {
'track': 'How to Make AI Models',
'lesson': 'The forward pass',
}
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
Training for an hour before you have printed one output shape. 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
List the three prints you want before the first update.
Self-check
- Say The forward pass 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.