AI engineering glossary · Deep learning core
What is LSTM?
LSTM (also called Long short-term memory): Long short-term memory, a recurrent unit with a separate memory cell and three gates (input, forget, output) that control what is written, kept or read. Its gating lets gradients flow over long spans, easing the vanishing-gradient problem of plain recurrent networks.
LSTM: an example
An LSTM can hold on to a subject seen 40 words earlier to choose the correct verb form.
Related terms
More Deep learning core terms
- Maxout
- Mixed precision training
- Model parallelism
- Multi-task learning
- Multilayer perceptron
- Negative log-likelihood
- Neural network pruning
- Neural tangent kernel
Where you learn it
LSTM is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.