Aarhus University Seal / Aarhus Universitets segl

Blazej Tadeusz Leporowski

Visualising deep network time-series representations

Publikation: Bidrag til tidsskrift/Konferencebidrag i tidsskrift /Bidrag til avisTidsskriftartikelForskningpeer review

DOI

Despite the popularisation of machine learning models, more often than not, they still operate as black boxes with no insight into what is happening inside the model. There exist a few methods that allow to visualise and explain why a model has made a certain prediction. Those methods, however, allow visualisation of the link between the input and output of the model without presenting how the model learns to represent the data used to train the model as whole. In this paper, a method that addresses that issue is proposed, with a focus on visualising multi-dimensional time-series data. Experiments on a high-frequency stock market dataset show that the method provides fast and discernible visualisations. Large datasets can be visualised quickly and on one plot, which makes it easy for a user to compare the learned representations of the data. The developed method successfully combines known techniques to provide an insight into the inner workings of time-series classification models.

OriginalsprogEngelsk
TidsskriftNeural Computing and Applications
Vol/bind33
Nummer23
Sider (fra-til)16489-16498
Antal sider10
ISSN0941-0643
DOI
StatusUdgivet - dec. 2021

Bibliografisk note

Funding Information:
Alexandros Iosifidis acknowledges funding from the Project DISPA (Grant 9041-00004B) funded by the Independent Research Fund Denmark.

Publisher Copyright:
© 2021, The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature.

Se relationer på Aarhus Universitet Citationsformater

ID: 226266993