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.
@article{arxiv.1905.10540,
title = {Dynamic Cell Structure via Recursive-Recurrent Neural Networks},
author = {Xin Qian and Matthew Kennedy and Diego Klabjan},
journal= {arXiv preprint arXiv:1905.10540},
year = {2019}
}