Deep learning-Autoencoders

Melle Vessies; Rutger van de Leur; Philippe Wouters; René van Es

doi:10.1007/978-3-031-36678-9_13

Deep learning-Autoencoders

Melle Vessies, Rutger van de Leur, Philippe Wouters, René van Es^*

^*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Chapter › Academic › peer-review

Abstract

Auto-encoders and their variational counterparts form a family of (deep) neural networks that serve a wide range of applications in medical research and clinical practice. In this chapter we provide a comprehensive overview of how auto-encoders work and how they can be used to improve medical research. We elaborate on various topics such as dimension reduction, denoising auto-encoders, auto-encoders used for anomaly detection and the applications of representations of data created using auto-encoders. Secondly, we touch upon the subject of variational auto-encoders, explaining their design and training process. We end the chapter with small scale examples of auto-encoders applied to the MNIST dataset and a recent example of an application of a (disentangled) variational auto-encoder applied to ECG-data.

Original language	English
Title of host publication	Clinical Applications of Artificial Intelligence in Real-World Data
Editors	Folkert W. Asselbergs, Spiros Denaxas, Daniel L. Oberski, Jason H. Moore
Publisher	Springer
Pages	203-220
Number of pages	18
Edition	1
ISBN (Electronic)	9783031366789
ISBN (Print)	9783031366772
DOIs	https://doi.org/10.1007/978-3-031-36678-9_13
Publication status	Published - 5 Nov 2023

Keywords

Anomaly detection
Auto-encoder
Deep learning
Denoising
Dimension reduction
Disentanglement
ECG
Explainable AI
Variational auto-encoder

Access to Document

10.1007/978-3-031-36678-9_13

Cite this

@inbook{081f25bde28841a7a41291ab69e0ec04,

title = "Deep learning-Autoencoders",

abstract = "Auto-encoders and their variational counterparts form a family of (deep) neural networks that serve a wide range of applications in medical research and clinical practice. In this chapter we provide a comprehensive overview of how auto-encoders work and how they can be used to improve medical research. We elaborate on various topics such as dimension reduction, denoising auto-encoders, auto-encoders used for anomaly detection and the applications of representations of data created using auto-encoders. Secondly, we touch upon the subject of variational auto-encoders, explaining their design and training process. We end the chapter with small scale examples of auto-encoders applied to the MNIST dataset and a recent example of an application of a (disentangled) variational auto-encoder applied to ECG-data.",

keywords = "Anomaly detection, Auto-encoder, Deep learning, Denoising, Dimension reduction, Disentanglement, ECG, Explainable AI, Variational auto-encoder",

author = "Melle Vessies and {van de Leur}, Rutger and Philippe Wouters and {van Es}, Ren{\'e}",

year = "2023",

month = nov,

day = "5",

doi = "10.1007/978-3-031-36678-9_13",

language = "English",

isbn = "9783031366772",

pages = "203--220",

editor = "Asselbergs, {Folkert W. } and Denaxas, {Spiros } and Oberski, {Daniel L. } and Moore, {Jason H. }",

booktitle = "Clinical Applications of Artificial Intelligence in Real-World Data",

publisher = "Springer",

edition = "1",

}

Deep learning-Autoencoders. / Vessies, Melle; van de Leur, Rutger; Wouters, Philippe et al.
Clinical Applications of Artificial Intelligence in Real-World Data. ed. / Folkert W. Asselbergs; Spiros Denaxas; Daniel L. Oberski; Jason H. Moore. 1. ed. Springer, 2023. p. 203-220.

Research output: Chapter in Book/Report/Conference proceeding › Chapter › Academic › peer-review

TY - CHAP

T1 - Deep learning-Autoencoders

AU - Vessies, Melle

AU - van de Leur, Rutger

AU - Wouters, Philippe

AU - van Es, René

PY - 2023/11/5

Y1 - 2023/11/5

N2 - Auto-encoders and their variational counterparts form a family of (deep) neural networks that serve a wide range of applications in medical research and clinical practice. In this chapter we provide a comprehensive overview of how auto-encoders work and how they can be used to improve medical research. We elaborate on various topics such as dimension reduction, denoising auto-encoders, auto-encoders used for anomaly detection and the applications of representations of data created using auto-encoders. Secondly, we touch upon the subject of variational auto-encoders, explaining their design and training process. We end the chapter with small scale examples of auto-encoders applied to the MNIST dataset and a recent example of an application of a (disentangled) variational auto-encoder applied to ECG-data.

AB - Auto-encoders and their variational counterparts form a family of (deep) neural networks that serve a wide range of applications in medical research and clinical practice. In this chapter we provide a comprehensive overview of how auto-encoders work and how they can be used to improve medical research. We elaborate on various topics such as dimension reduction, denoising auto-encoders, auto-encoders used for anomaly detection and the applications of representations of data created using auto-encoders. Secondly, we touch upon the subject of variational auto-encoders, explaining their design and training process. We end the chapter with small scale examples of auto-encoders applied to the MNIST dataset and a recent example of an application of a (disentangled) variational auto-encoder applied to ECG-data.

KW - Anomaly detection

KW - Auto-encoder

KW - Deep learning

KW - Denoising

KW - Dimension reduction

KW - Disentanglement

KW - ECG

KW - Explainable AI

KW - Variational auto-encoder

UR - http://www.scopus.com/inward/record.url?scp=85194455221&partnerID=8YFLogxK

U2 - 10.1007/978-3-031-36678-9_13

DO - 10.1007/978-3-031-36678-9_13

M3 - Chapter

AN - SCOPUS:85194455221

SN - 9783031366772

SP - 203

EP - 220

BT - Clinical Applications of Artificial Intelligence in Real-World Data

A2 - Asselbergs, Folkert W.

A2 - Denaxas, Spiros

A2 - Oberski, Daniel L.

A2 - Moore, Jason H.

PB - Springer

ER -

Deep learning-Autoencoders

Abstract

Keywords

Access to Document

Other files and links

Cite this