Recurrent neural network
class of artificial neural network where connections between units form a directed graph along a temporal sequence From Wikipedia, the free encyclopedia
Remove ads
A recurrent neural network (RNN) is a special type of artificial neural network (a computer program) that can remember things it has seen before. RNNs do this by connecting information from the past (called a hidden state) with new information.[1] Because of this, RNNs are good at processing data in a sequence, like understanding language, translating between languages, or predicting what might come next in a sequence.[2]
Remove ads
References
Wikiwand - on
Seamless Wikipedia browsing. On steroids.
Remove ads