Zobrazeno 1 - 1
of 1
pro vyhledávání: '"Xu, Jian"'
Publikováno v:
Applied Mathematics and Nonlinear Sciences, Vol 8, Iss 1, Pp 55-68 (2023)
Although the traditional recurrent neural network (RNN) model can cover the time information of the whole sentence theoretically, the gradient is dominated by the short-term gradient, and the long-term gradient is very small, which makes it difficult
Externí odkaz:
https://doaj.org/article/dd34b904443a4fb785a79d978e8a6ad6