AI engineering glossary · Deep learning core
What is STE (straight-through estimator)?
Straight-through estimator (also called STE): A trick for training through operations with zero or undefined gradients, such as rounding or thresholding. It uses the operation in the forward pass but pretends it was the identity in the backward pass so learning can continue.
Straight-through estimator: an example
In quantisation-aware training, rounding weights to integers is bypassed by copying the gradient straight through.
Related terms
More Deep learning core terms
- SwiGLU
- Symmetry breaking
- Tanh
- Teacher forcing
- Training loop
- Universal approximation theorem
- Validation loss
- Vanishing gradient
Where you learn it
Straight-through estimator is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.