RNN — Recurrent Neural Network
Definition: A network architecture that processes sequences by maintaining state across steps. Mostly displaced by transformers for language, but still useful where compute is tight and sequences are short.
Example
For on-device sensor data, an RNN fits in 200KB and runs offline — a transformer would never have shipped.
When you'll hear it
RNN shows up most often in AI strategy reviews, model evaluation discussions, and product roadmap meetings. When someone uses it, they're usually referring to recurrent neural network — and they expect the room to already know what that means.
FAQs
What does RNN stand for?
RNN stands for Recurrent Neural Network.
What does RNN mean in AI and machine-learning?
A network architecture that processes sequences by maintaining state across steps. Mostly displaced by transformers for language, but still useful where compute is tight and sequences are short.
Where will I hear RNN used at work?
RNN comes up most often in AI strategy reviews, model evaluation discussions, and product roadmap meetings. It's used as shorthand for recurrent neural network, so people assume you already know the term.