Üçlü Kayip Maliyetli Deǧisken Otokodlayicilar ile Temsil Öǧrenimi

Cagatay Isil; Berkan Solmaz; Aykut Koc

doi:10.1109/SIU.2018.8404227

Üçlü Kayip Maliyetli Deǧisken Otokodlayicilar ile Temsil Öǧrenimi

Translated title of the contribution: Variational autoencoders with triplet loss for representation learning

Cagatay Isil, Berkan Solmaz, Aykut Koc

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

Learning low dimensional meaningful representations of data is an important task for classification, visualization and compression. Using autoencoders for representation learning is a successful application of deep learning. Recently, variational autoencoders have also been developed. These are more advantageous than autoencoders since these are generative and have a compact form in the latent space. In order to improve the clustering performance of variational autoencoders in the latent space, the use of variational autoencoders with triplet loss is proposed in this study.

Original language	Turkish
Title of host publication	26th IEEE Signal Processing and Communications Applications Conference, SIU 2018
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	1-4
Number of pages	4
ISBN (Electronic)	9781538615010
DOIs	https://doi.org/10.1109/SIU.2018.8404227
Publication status	Published - Jul 5 2018
Externally published	Yes
Event	26th IEEE Signal Processing and Communications Applications Conference, SIU 2018 - Izmir, Turkey Duration: May 2 2018 → May 5 2018

Publication series

Name	26th IEEE Signal Processing and Communications Applications Conference, SIU 2018

Conference

Conference
Country	Turkey
City	Izmir
Period	5/2/18 → 5/5/18

Fingerprint

Keywords

Autoencoders
Deep learning
Representation learning
Triplet loss

ASJC Scopus subject areas

Artificial Intelligence
Computer Networks and Communications
Computer Science Applications
Signal Processing

Cite this

Isil, C., Solmaz, B., & Koc, A. (2018). Üçlü Kayip Maliyetli Deǧisken Otokodlayicilar ile Temsil Öǧrenimi. In 26th IEEE Signal Processing and Communications Applications Conference, SIU 2018 (pp. 1-4). (26th IEEE Signal Processing and Communications Applications Conference, SIU 2018). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/SIU.2018.8404227

Üçlü Kayip Maliyetli Deǧisken Otokodlayicilar ile Temsil Öǧrenimi. / Isil, Cagatay; Solmaz, Berkan; Koc, Aykut.

26th IEEE Signal Processing and Communications Applications Conference, SIU 2018. Institute of Electrical and Electronics Engineers Inc., 2018. p. 1-4 (26th IEEE Signal Processing and Communications Applications Conference, SIU 2018).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Isil, C, Solmaz, B & Koc, A 2018, Üçlü Kayip Maliyetli Deǧisken Otokodlayicilar ile Temsil Öǧrenimi. in 26th IEEE Signal Processing and Communications Applications Conference, SIU 2018. 26th IEEE Signal Processing and Communications Applications Conference, SIU 2018, Institute of Electrical and Electronics Engineers Inc., pp. 1-4, 26th IEEE Signal Processing and Communications Applications Conference, SIU 2018, Izmir, Turkey, 5/2/18. https://doi.org/10.1109/SIU.2018.8404227

Isil C, Solmaz B, Koc A. Üçlü Kayip Maliyetli Deǧisken Otokodlayicilar ile Temsil Öǧrenimi. In 26th IEEE Signal Processing and Communications Applications Conference, SIU 2018. Institute of Electrical and Electronics Engineers Inc. 2018. p. 1-4. (26th IEEE Signal Processing and Communications Applications Conference, SIU 2018). https://doi.org/10.1109/SIU.2018.8404227

@inproceedings{f69fd9f130e740f29dfbbe8d72263abf,

title = "{\"U}{\cc}l{\"u} Kayip Maliyetli Deǧisken Otokodlayicilar ile Temsil {\"O}ǧrenimi",

abstract = "Learning low dimensional meaningful representations of data is an important task for classification, visualization and compression. Using autoencoders for representation learning is a successful application of deep learning. Recently, variational autoencoders have also been developed. These are more advantageous than autoencoders since these are generative and have a compact form in the latent space. In order to improve the clustering performance of variational autoencoders in the latent space, the use of variational autoencoders with triplet loss is proposed in this study.",

keywords = "Autoencoders, Deep learning, Representation learning, Triplet loss",

author = "Cagatay Isil and Berkan Solmaz and Aykut Koc",

year = "2018",

month = "7",

day = "5",

doi = "10.1109/SIU.2018.8404227",

language = "Turkish",

series = "26th IEEE Signal Processing and Communications Applications Conference, SIU 2018",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "1--4",

booktitle = "26th IEEE Signal Processing and Communications Applications Conference, SIU 2018",

note = "26th IEEE Signal Processing and Communications Applications Conference, SIU 2018 ; Conference date: 02-05-2018 Through 05-05-2018",

}

TY - GEN

T1 - Üçlü Kayip Maliyetli Deǧisken Otokodlayicilar ile Temsil Öǧrenimi

AU - Isil, Cagatay

AU - Solmaz, Berkan

AU - Koc, Aykut

PY - 2018/7/5

Y1 - 2018/7/5

N2 - Learning low dimensional meaningful representations of data is an important task for classification, visualization and compression. Using autoencoders for representation learning is a successful application of deep learning. Recently, variational autoencoders have also been developed. These are more advantageous than autoencoders since these are generative and have a compact form in the latent space. In order to improve the clustering performance of variational autoencoders in the latent space, the use of variational autoencoders with triplet loss is proposed in this study.

AB - Learning low dimensional meaningful representations of data is an important task for classification, visualization and compression. Using autoencoders for representation learning is a successful application of deep learning. Recently, variational autoencoders have also been developed. These are more advantageous than autoencoders since these are generative and have a compact form in the latent space. In order to improve the clustering performance of variational autoencoders in the latent space, the use of variational autoencoders with triplet loss is proposed in this study.

KW - Autoencoders

KW - Deep learning

KW - Representation learning

KW - Triplet loss

UR - http://www.scopus.com/inward/record.url?scp=85050825414&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85050825414&partnerID=8YFLogxK

U2 - 10.1109/SIU.2018.8404227

DO - 10.1109/SIU.2018.8404227

M3 - Conference contribution

AN - SCOPUS:85050825414

T3 - 26th IEEE Signal Processing and Communications Applications Conference, SIU 2018

SP - 1

EP - 4

BT - 26th IEEE Signal Processing and Communications Applications Conference, SIU 2018

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 26th IEEE Signal Processing and Communications Applications Conference, SIU 2018

Y2 - 2 May 2018 through 5 May 2018

ER -

Access to Document

10.1109/SIU.2018.8404227