AI engineering glossary · Deep learning core
What is teacher forcing?
Teacher forcing: A training method for sequence models in which the true previous token, rather than the model's own earlier prediction, is fed as the next input. It speeds and stabilises learning but creates a mismatch with generation time.
Teacher forcing: an example
When training a translator, the correct first word is provided when predicting the second, even if the model guessed wrongly.
Related terms
- Recurrent neural network
- Training loop
- Loss function
More Deep learning core terms
- Training loop
- Universal approximation theorem
- Validation loss
- Vanishing gradient
- Weight decay
- Weight initialisation
- Weight normalisation
- Weight sharing
Where you learn it
Teacher forcing is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.