Recurrent Neural Network

A neural network that processes sequences one step at a time, passing a hidden state from each step to the next. RNNs were the standard tool for language and time-series tasks before transformers, and variants such as LSTM and GRU helped with the vanishing-gradient problem. Most new sequence models today are transformer-based, but RNNs still appear in low-latency settings.

Definición editorial de DecipherU. Para definiciones técnicas autorizadas, consulta NIST AI RMF, ISO/IEC 42001, o las publicaciones oficiales de los laboratorios de IA.