Can I read Exploring Interpretable LSTM Neural Networks over Multi-Variable Data on EtoBox?

Exploring Interpretable LSTM Neural Networks over Multi-Variable Data by Guo, Tian; Lin, Tao; Antulov-Fantulin, Nino is a scholarly article available to read on EtoBox.

What is Exploring Interpretable LSTM Neural Networks over Multi-Variable Data about?

For recurrent neural networks trained on time series with target and exogenous variables, in addition to accurate prediction, it is also desired to provide interpretable insights into the data. In this paper, we explore the structure of LSTM recurrent neural networks to learn variable-wise hidden states, with the aim to capture different dynamics in multi-variable time series and distinguish the contribution of variables to the prediction. With these variable-wise hidden states, a mixture attention mechanism is proposed to model the generative process of the target. Then we develop associated training methods to jointly learn network parameters, variable and temporal importance w.r.t the prediction of the target variable. Extensive experiments on real datasets demonstrate enhanced prediction performance by capturing the dynamics of different variables. Meanwhile, we evaluate the interpretation results both qualitatively and quantitatively. It exhibits the prospect as an end-to-end framework for both forecasting and knowledge extraction over multi-variable data.

Author

Guo, Tian; Lin, Tao; Antulov-Fantulin, Nino

Published

2019

Language

EN