arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1807.09830cs.LGcs.NEstat.ML
收藏

LSTM细胞的迭代评估

Iterative evaluation of LSTM cells

Universidad de Buenos Aires(布宜诺斯艾利斯大学);Universidad Nacional de Tres de Febrero(二月三日国立大学)

Leandro Palma, Luis Argerich

摘要:

在这项工作中,我们提出了通过LSTM网络的传统信息流的修改,我们认为它通常非常适合RNN。这种修改导致了一种迭代方案,其中LSTM单元执行的计算在恒定的输入和单元状态值上重复,同时更新隐藏状态有限次。我们提供了理论和经验证据来支持迭代方案的增强功能,并显示与语言建模相关的示例。修改产生的增强模型的性能相比,原模型增加了3倍以上的参数的总量。

英文摘要:

In this work we present a modification in the conventional flow of information through a LSTM network, which we consider well suited for RNNs in general. The modification leads to a iterative scheme where the computations performed by the LSTM cell are repeated over a constant input and cell state values, while updating the hidden state a finite number of times. We provide theoretical and empirical evidence to support the augmented capabilities of the iterative scheme and show examples related to language modeling. The modification yields an enhancement in the model performance comparable with the original model augmented more than 3 times in terms of the total amount of parameters.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑