MinimalRNN: Toward More Interpretable and Trainable Recurrent Neural Networks
Machine Learning
2018-06-21 v2 Machine Learning
Abstract
We introduce MinimalRNN, a new recurrent neural network architecture that achieves comparable performance as the popular gated RNNs with a simplified structure. It employs minimal updates within RNN, which not only leads to efficient learning and testing but more importantly better interpretability and trainability. We demonstrate that by endorsing the more restrictive update rule, MinimalRNN learns disentangled RNN states. We further examine the learning dynamics of different RNN structures using input-output Jacobians, and show that MinimalRNN is able to capture longer range dependencies than existing RNN architectures.
Cite
@article{arxiv.1711.06788,
title = {MinimalRNN: Toward More Interpretable and Trainable Recurrent Neural Networks},
author = {Minmin Chen},
journal= {arXiv preprint arXiv:1711.06788},
year = {2018}
}
Comments
Presented at NIPS 2017 Symposium on Interpretable Machine Learning