Embeddings on the How to Make AI Models track. An embedding maps an id or token to a vector trained for the task. Similar ids can land nearby if the data supports it. The table size is vocabulary times dimension.
This lesson assumes you already worked through Activation functions.
The idea in practice
Reserve a row for unknown ids. Do not embed a unique user id with one row each if users do not repeat.
A concrete check
goal = {
'track': 'How to Make AI Models',
'lesson': 'Embeddings',
}
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
An embedding larger than the dataset with no sharing. 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
Compute a rough parameter count for a 30,000-word vocabulary and 128 dimensions.
Self-check
- Say Embeddings 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.