Recurrent neural network: Difference between revisions

Revision as of 11:26, 18 July 2025

Revision as of 14:06, 20 July 2025

Line 1:

{{Short description|Class of artificial neural network}}

{{Distinguish|Recursive neural network|Feedback neural network}}

{{Machine learning|Neural networks}}

Line 38:

==Configurations==

{{main|Layer (deep learning)}}

An RNN-based model can be factored into two parts: configuration and architecture. Multiple RNNs can be combined in a data flow, and the data flow itself is the configuration. Each RNN itself may have any architecture, including LSTM, GRU, etc.