AI engineering glossary · Deep learning core
What is gating mechanism?
Gating mechanism (also called Gate): A learned multiplier between 0 and 1, usually produced by a sigmoid, that decides how much of a signal passes through. Gates let networks such as LSTMs and GRUs choose what to remember, forget or expose.
Gating mechanism: an example
A forget gate value of 0.1 keeps only 10 percent of the old memory.
Related terms
More Deep learning core terms
- GELU
- Gradient checkpointing
- Gradient norm
- Group normalisation
- GRU
- He initialisation
- Hidden layer
- Hidden state
Where you learn it
Gating mechanism is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.