Abstract
In a recurrent setting, conventional approaches to neural architecture search find and fix a general model for all data samples and time steps. We propose a novel algorithm that can dynamically search for the structure of cells in a recurrent neural network model. Based on a combination of recurrent and recursive neural networks, our algorithm is able to construct customized cell structures for each data sample and time step, allowing for a more efficient architecture search than existing models. Experiments on three common datasets show that the algorithm discovers high-performance cell architectures and achieves better prediction accuracy compared to the GRU structure for language modelling and sentiment analysis.
Abstract (translated)
在一个反复出现的环境中，传统的神经架构搜索方法可以找到并修复所有数据样本和时间步骤的通用模型。我们提出了一种新的算法，可以在一个循环神经网络模型中动态搜索细胞结构。基于递归和递归神经网络的结合，我们的算法能够为每个数据样本和时间步构建定制的单元结构，从而比现有的模型更高效地进行架构搜索。对三个常用数据集的实验表明，该算法发现了高性能的单元结构，在语言建模和情感分析方面，与GRU结构相比，具有更好的预测精度。
URL
https://arxiv.org/abs/1905.10540
