TY - GEN
T1 - Adaptive Loss Function Design Algorithm for Input Data Distribution in Autoencoder
AU - Rheey, Joohong
AU - Choi, Dayoung
AU - Park, Hyunggon
N1 - Funding Information:
This work was supported in part by Institute of Information & communications Technology Planning & Evaluation (IITP) grant funded by the Korea government (MSIT) (No.2021-0- 00739, Development of Distributed/Cooperative AI based 5G+ Network Data Analytics Functions and Control Technology) and supported in part by the National Research Foundation of Korea (NRF) grant funded by the Korea government (MSIT)(No. NRF-2020R1A2B5B01002528).
Funding Information:
ACKNOWLEDGMENT This work was supported in part by Institute of Information & communications Technology Planning & Evaluation (IITP) grant funded by the Korea government (MSIT) (No.2021-0-00739, Development of Distributed/Cooperative AI based 5G+ Network Data Analytics Functions and Control Technology) and supported in part by the National Research Foundation of Korea (NRF) grant funded by the Korea government (MSIT)(No. NRF-2020R1A2B5B01002528).
Publisher Copyright:
© 2022 IEEE.
PY - 2022
Y1 - 2022
N2 - 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.
AB - 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.
KW - Autoencoder
KW - data distribution
KW - KL divergence
KW - loss function
KW - training performance
UR - http://www.scopus.com/inward/record.url?scp=85143252788&partnerID=8YFLogxK
U2 - 10.1109/ICTC55196.2022.9952422
DO - 10.1109/ICTC55196.2022.9952422
M3 - Conference contribution
AN - SCOPUS:85143252788
T3 - International Conference on ICT Convergence
SP - 489
EP - 491
BT - ICTC 2022 - 13th International Conference on Information and Communication Technology Convergence
PB - IEEE Computer Society
T2 - 13th International Conference on Information and Communication Technology Convergence, ICTC 2022
Y2 - 19 October 2022 through 21 October 2022
ER -