Jump to content

Recurrent neural network

From Wikipedia, the free encyclopedia
This is an old revision of this page, as edited by Tyrell turing (talk | contribs) at 20:49, 7 April 2005. The present address (URL) is a permanent link to this revision, which may differ significantly from the current revision.
(diff) ← Previous revision | Latest revision (diff) | Newer revision → (diff)

A recurrent neural network is a neural network where the connections amongst the units form a directed cycle. Recurrent neural networks must be approached differently than feedforward neural networks, both in training them and the analysing their behavior.