paper-with-me

홈 › Papers

Exploring Interpretable LSTM Neural Networks over Multi-Variable Data

2019-05-28 · Tian Guo, Tao Lin, Nino Antulov-Fantulin

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.

📄 PDF Abstract BibTeX arXiv:1905.12034

Code (3)

KurochkinAlexey/IMV_LSTM pytorch
jessejhang/imv-lstm pytorch
licheng0794/IMV-LSTM-Classfication pytorch

Tasks

PredictionTime SeriesTime Series Analysis

Methods 이 논문이 사용한 방법론

Sigmoid Activation 설명 없음
Tanh Activation 설명 없음
LSTM An LSTM is a type of recurrent neural network that addresses the vanishing gradient problem in vanilla…

Similar Papers 제목 키워드 기반

Exploring the interpretability of LSTM neural networks over multi-variable data

2018-09-27 · Tian Guo, Tao Lin

In learning a predictive model over multivariate time series consisting of target and exogenous variables, the forecasting performance and interpretability of the model are both essential for deployment and uncovering kn…

Time SeriesTime Series Analysis

An interpretable LSTM neural network for autoregressive exogenous model

2018-04-14 · Tian Guo, Tao Lin, Yao Lu

In this paper, we propose an interpretable LSTM recurrent neural network, i.e., multi-variable LSTM for time series with exogenous variables. Currently, widely used attention mechanism in recurrent neural networks mostly…

DecoderTime SeriesTime Series Analysis

Exploring Neural Models for Parsing Natural Language into First-Order Logic

2020-02-16 · Hrituraj Singh, Milan Aggrawal, Balaji Krishnamurthy

Semantic parsing is the task of obtaining machine-interpretable representations from natural language text. We consider one such formal representation - First-Order Logic (FOL) and explore the capability of neural models…

DecoderSemantic ParsingSentence

Exploring Neural Granger Causality with xLSTMs: Unveiling Temporal Dependencies in Complex Data

2025-02-14 · Harsh Poonia, Felix Divo, Kristian Kersting, Devendra Singh Dhami

Causality in time series can be difficult to determine, especially in the presence of non-linear dependencies. The concept of Granger causality helps analyze potential relationships between variables, thereby offering a …

Time Series

Exploring Transformer-Augmented LSTM for Temporal and Spatial Feature Learning in Trajectory Prediction

2024-12-18 · Chandra Raskoti, Weizi Li

Accurate vehicle trajectory prediction is crucial for ensuring safe and efficient autonomous driving. This work explores the integration of Transformer based model with Long Short-Term Memory (LSTM) based technique to en…

Autonomous DrivingPredictionTrajectory Prediction