Deep learning: RNNs and LSTM

Robert DiPietro; Gregory D. Hager

doi:10.1016/B978-0-12-816176-0.00026-0

Deep learning: RNNs and LSTM

Robert DiPietro, Gregory D. Hager

Whiting School of Engineering

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

11 Scopus citations

Abstract

Recurrent neural networks (RNNs) are a class of neural networks that are naturally suited to processing time-series data and other sequential data. Here we introduce recurrent neural networks as an extension to feedforward networks, in order to allow the processing of variable-length (or even infinite-length) sequences, and some of the most popular recurrent architectures in use, including long short-term memory (LSTM) and gated recurrent units (GRUs). In addition, various aspects surrounding RNNs are discussed in detail, including various probabilistic models that are often realized using RNNs and various applications of RNNs that have appeared within the MICCAI community.

Original language	English (US)
Title of host publication	Handbook of Medical Image Computing and Computer Assisted Intervention
Publisher	Elsevier
Pages	503-519
Number of pages	17
ISBN (Electronic)	9780128161760
DOIs	https://doi.org/10.1016/B978-0-12-816176-0.00026-0
State	Published - Jan 1 2019

Keywords

Long short-term memory
Recurrent neural networks

ASJC Scopus subject areas

General Computer Science

Access to Document

10.1016/B978-0-12-816176-0.00026-0

Cite this

@inbook{526237cf43a64b72a0b27ace04931aed,

title = "Deep learning: RNNs and LSTM",

abstract = "Recurrent neural networks (RNNs) are a class of neural networks that are naturally suited to processing time-series data and other sequential data. Here we introduce recurrent neural networks as an extension to feedforward networks, in order to allow the processing of variable-length (or even infinite-length) sequences, and some of the most popular recurrent architectures in use, including long short-term memory (LSTM) and gated recurrent units (GRUs). In addition, various aspects surrounding RNNs are discussed in detail, including various probabilistic models that are often realized using RNNs and various applications of RNNs that have appeared within the MICCAI community.",

keywords = "Long short-term memory, Recurrent neural networks",

author = "Robert DiPietro and Hager, {Gregory D.}",

year = "2019",

month = jan,

day = "1",

doi = "10.1016/B978-0-12-816176-0.00026-0",

language = "English (US)",

pages = "503--519",

booktitle = "Handbook of Medical Image Computing and Computer Assisted Intervention",

publisher = "Elsevier",

}

TY - CHAP

T1 - Deep learning

T2 - RNNs and LSTM

AU - DiPietro, Robert

AU - Hager, Gregory D.

PY - 2019/1/1

Y1 - 2019/1/1

N2 - Recurrent neural networks (RNNs) are a class of neural networks that are naturally suited to processing time-series data and other sequential data. Here we introduce recurrent neural networks as an extension to feedforward networks, in order to allow the processing of variable-length (or even infinite-length) sequences, and some of the most popular recurrent architectures in use, including long short-term memory (LSTM) and gated recurrent units (GRUs). In addition, various aspects surrounding RNNs are discussed in detail, including various probabilistic models that are often realized using RNNs and various applications of RNNs that have appeared within the MICCAI community.

AB - Recurrent neural networks (RNNs) are a class of neural networks that are naturally suited to processing time-series data and other sequential data. Here we introduce recurrent neural networks as an extension to feedforward networks, in order to allow the processing of variable-length (or even infinite-length) sequences, and some of the most popular recurrent architectures in use, including long short-term memory (LSTM) and gated recurrent units (GRUs). In addition, various aspects surrounding RNNs are discussed in detail, including various probabilistic models that are often realized using RNNs and various applications of RNNs that have appeared within the MICCAI community.

KW - Long short-term memory

KW - Recurrent neural networks

UR - http://www.scopus.com/inward/record.url?scp=85082586402&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85082586402&partnerID=8YFLogxK

U2 - 10.1016/B978-0-12-816176-0.00026-0

DO - 10.1016/B978-0-12-816176-0.00026-0

M3 - Chapter

AN - SCOPUS:85082586402

SP - 503

EP - 519

BT - Handbook of Medical Image Computing and Computer Assisted Intervention

PB - Elsevier

ER -

Deep learning: RNNs and LSTM

Abstract

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this