Aarhus Universitets segl

Blazej Tadeusz Leporowski

Visualising deep network time-series representations

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

Standard

Visualising deep network time-series representations. / Leporowski, Błażej; Iosifidis, Alexandros.

I: Neural Computing and Applications, Bind 33, Nr. 23, 12.2021, s. 16489-16498.

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

Harvard

APA

CBE

MLA

Vancouver

Author

Leporowski, Błażej ; Iosifidis, Alexandros. / Visualising deep network time-series representations. I: Neural Computing and Applications. 2021 ; Bind 33, Nr. 23. s. 16489-16498.

Bibtex

@article{8824e46af4214ec089bd1cbb32057426,
title = "Visualising deep network time-series representations",
abstract = "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.",
keywords = "Financial data, Limit order book, Neural network representations visualisation, Time-series visualisation",
author = "B{\l}a{\.z}ej Leporowski and Alexandros Iosifidis",
note = "Publisher Copyright: {\textcopyright} 2021, The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature.",
year = "2021",
month = dec,
doi = "10.1007/s00521-021-06244-8",
language = "English",
volume = "33",
pages = "16489--16498",
journal = "Neural Computing and Applications",
issn = "0941-0643",
publisher = "Springer",
number = "23",

}

RIS

TY - JOUR

T1 - Visualising deep network time-series representations

AU - Leporowski, Błażej

AU - Iosifidis, Alexandros

N1 - Publisher Copyright: © 2021, The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature.

PY - 2021/12

Y1 - 2021/12

N2 - 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.

AB - 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.

KW - Financial data

KW - Limit order book

KW - Neural network representations visualisation

KW - Time-series visualisation

UR - http://www.scopus.com/inward/record.url?scp=85109655970&partnerID=8YFLogxK

U2 - 10.1007/s00521-021-06244-8

DO - 10.1007/s00521-021-06244-8

M3 - Journal article

AN - SCOPUS:85109655970

VL - 33

SP - 16489

EP - 16498

JO - Neural Computing and Applications

JF - Neural Computing and Applications

SN - 0941-0643

IS - 23

ER -