Adaptive Loss Function Design Algorithm for Input Data Distribution in Autoencoder

Joohong Rheey, Dayoung Choi, Hyunggon Park

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

1 Scopus citations

Abstract

The training performance of an autoencoder is significantly affected by its loss function. In order to improve the performance of autoencoders, it is important to design ap-propriate loss functions. However, many loss functions have been designed without taking into account the characteristics of the input data distribution. In this paper, we propose an algorithm for the design of a loss function by adaptively determining optimal parameters to input data distribution. Specifically, the proposed optimal parameters for loss function are determined by explicitly considering the dependency of the standard deviation of input data distribution. The simulation results confirm that the pro-posed algorithm can improve traditional loss functions. Moreover, the loss function determined by the proposed algorithm can reduce the computational complexity for training autoencoders.

Original languageEnglish
Title of host publicationICTC 2022 - 13th International Conference on Information and Communication Technology Convergence
Subtitle of host publicationAccelerating Digital Transformation with ICT Innovation
PublisherIEEE Computer Society
Pages489-491
Number of pages3
ISBN (Electronic)9781665499392
DOIs
StatePublished - 2022
Event13th International Conference on Information and Communication Technology Convergence, ICTC 2022 - Jeju Island, Korea, Republic of
Duration: 19 Oct 202221 Oct 2022

Publication series

NameInternational Conference on ICT Convergence
Volume2022-October
ISSN (Print)2162-1233
ISSN (Electronic)2162-1241

Conference

Conference13th International Conference on Information and Communication Technology Convergence, ICTC 2022
Country/TerritoryKorea, Republic of
CityJeju Island
Period19/10/2221/10/22

Bibliographical note

Publisher Copyright:
© 2022 IEEE.

Keywords

  • Autoencoder
  • KL divergence
  • data distribution
  • loss function
  • training performance

Fingerprint

Dive into the research topics of 'Adaptive Loss Function Design Algorithm for Input Data Distribution in Autoencoder'. Together they form a unique fingerprint.

Cite this