View : 277 Download: 0

Neural additive time-series models: Explainable deep learning for multivariate time-series prediction

Title
Neural additive time-series models: Explainable deep learning for multivariate time-series prediction
Authors
JoWonkeunKimDongil
Ewha Authors
김동일
SCOPUS Author ID
김동일scopus
Issue Date
2023
Journal Title
Expert Systems with Applications
ISSN
0957-4174JCR Link
Citation
Expert Systems with Applications vol. 228
Keywords
Deep learningExplainable artificial intelligenceMultivariate time series predictionNeural additive modelsParameter sharing
Publisher
Elsevier Ltd
Indexed
SCIE; SCOPUS WOS scopus
Document Type
Article
Abstract
Deep neural networks are one of the most important methods in machine learning. The advantages of neural networks are their excellent prediction performance and versatility using deep architecture and generalized input–output forms. However, as neural networks are black-box models, they lack explanatory power for their predictions. In this study, we propose a new neural network architecture that includes the interpretability of predictions for multivariate time-series (MTS) data by employing a generalized additive method. In addition, we examine parameter sharing networks to decrease the model's complexity, along with hard-shared networks. We conducted experiments to demonstrate that the interpretable neural architecture can quantify the contributions of each input value to the prediction of each MTS by every time step and variable. Experimental results involving a toy example and four real-world datasets demonstrate that the performance of the proposed method in predicting MTS data is comparable to that of state-of-the-art neural networks, while providing reasonable importance for each input value. © 2023 Elsevier Ltd
DOI
10.1016/j.eswa.2023.120307
Appears in Collections:
ETC > ETC
Files in This Item:
There are no files associated with this item.
Export
RIS (EndNote)
XLS (Excel)
XML


qrcode

BROWSE