The Statistical Recurrent Unit
Abstract
Sophisticated gated recurrent neural network architectures like LSTMs and GRUs have been shown to be highly effective in a myriad of applications. We develop an un-gated unit, the statistical recurrent unit (SRU), that is able to learn long term dependencies in data by only keeping moving averages of statistics. The SRU’s architecture is simple, un-gated, and contains a comparable number of parameters to LSTMs; yet, SRUs perform favorably to more sophisticated LSTM and GRU alternatives, often outperforming one or both in various tasks. We show the efficacy of SRUs as compared to LSTMs and GRUs in an unbiased manner by optimizing respective architectures’ hyperparameters for both synthetic and real-world tasks.
Cite
Text
Oliva et al. "The Statistical Recurrent Unit." International Conference on Machine Learning, 2017.Markdown
[Oliva et al. "The Statistical Recurrent Unit." International Conference on Machine Learning, 2017.](https://mlanthology.org/icml/2017/oliva2017icml-statistical/)BibTeX
@inproceedings{oliva2017icml-statistical,
title = {{The Statistical Recurrent Unit}},
author = {Oliva, Junier B. and Póczos, Barnabás and Schneider, Jeff},
booktitle = {International Conference on Machine Learning},
year = {2017},
pages = {2671-2680},
volume = {70},
url = {https://mlanthology.org/icml/2017/oliva2017icml-statistical/}
}