Compositional deep learning in Futhark

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

Standard

Compositional deep learning in Futhark. / Tran, Duc Minh; Henriksen, Troels; Elsman, Martin.

FHPNC 2019 - Proceedings of the 8th ACM SIGPLAN International Workshop on Functional High-Performance and Numerical Computing, co-located with ICFP 2019. ed. / Marco Zocca. Association for Computing Machinery, 2019. p. 47-59.

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

Harvard

Tran, DM, Henriksen, T & Elsman, M 2019, Compositional deep learning in Futhark. in M Zocca (ed.), FHPNC 2019 - Proceedings of the 8th ACM SIGPLAN International Workshop on Functional High-Performance and Numerical Computing, co-located with ICFP 2019. Association for Computing Machinery, pp. 47-59, 8th ACM SIGPLAN International Workshop on Functional High-Performance and Numerical Computing, FHPNC 2019, co-located with ICFP 2019, Berlin, Germany, 18/08/2019. https://doi.org/10.1145/3331553.3342617

APA

Tran, D. M., Henriksen, T., & Elsman, M. (2019). Compositional deep learning in Futhark. In M. Zocca (Ed.), FHPNC 2019 - Proceedings of the 8th ACM SIGPLAN International Workshop on Functional High-Performance and Numerical Computing, co-located with ICFP 2019 (pp. 47-59). Association for Computing Machinery. https://doi.org/10.1145/3331553.3342617

Vancouver

Tran DM, Henriksen T, Elsman M. Compositional deep learning in Futhark. In Zocca M, editor, FHPNC 2019 - Proceedings of the 8th ACM SIGPLAN International Workshop on Functional High-Performance and Numerical Computing, co-located with ICFP 2019. Association for Computing Machinery. 2019. p. 47-59 https://doi.org/10.1145/3331553.3342617

Author

Tran, Duc Minh ; Henriksen, Troels ; Elsman, Martin. / Compositional deep learning in Futhark. FHPNC 2019 - Proceedings of the 8th ACM SIGPLAN International Workshop on Functional High-Performance and Numerical Computing, co-located with ICFP 2019. editor / Marco Zocca. Association for Computing Machinery, 2019. pp. 47-59

Bibtex

@inproceedings{f24d3b05a9a14d1f993fed1a69b7a2b6,
title = "Compositional deep learning in Futhark",
abstract = "We present a design pattern for composing deep learning networks in a typed, higher-order fashion. The exposed library functions are generically typed and the composition structure allows for networks to be trained (using backpropagation) and for trained networks to be used for predicting new results (using forward-propagation). Individual layers in a network can take different forms ranging over dense sigmoid layers to convolutional layers. The paper discusses different typing techniques aimed at enforcing proper use and composition of networks. The approach is implemented in Futhark, a data-parallel functional language and compiler targeting GPU architectures, and we demonstrate that Futhark's elimination of higher-order functions and modules leads to efficient generated code.",
keywords = "Data-parallelism, Deep learning, Functional languages",
author = "Tran, {Duc Minh} and Troels Henriksen and Martin Elsman",
year = "2019",
month = aug,
day = "18",
doi = "10.1145/3331553.3342617",
language = "English",
pages = "47--59",
editor = "Marco Zocca",
booktitle = "FHPNC 2019 - Proceedings of the 8th ACM SIGPLAN International Workshop on Functional High-Performance and Numerical Computing, co-located with ICFP 2019",
publisher = "Association for Computing Machinery",
note = "8th ACM SIGPLAN International Workshop on Functional High-Performance and Numerical Computing, FHPNC 2019, co-located with ICFP 2019 ; Conference date: 18-08-2019",

}

RIS

TY - GEN

T1 - Compositional deep learning in Futhark

AU - Tran, Duc Minh

AU - Henriksen, Troels

AU - Elsman, Martin

PY - 2019/8/18

Y1 - 2019/8/18

N2 - We present a design pattern for composing deep learning networks in a typed, higher-order fashion. The exposed library functions are generically typed and the composition structure allows for networks to be trained (using backpropagation) and for trained networks to be used for predicting new results (using forward-propagation). Individual layers in a network can take different forms ranging over dense sigmoid layers to convolutional layers. The paper discusses different typing techniques aimed at enforcing proper use and composition of networks. The approach is implemented in Futhark, a data-parallel functional language and compiler targeting GPU architectures, and we demonstrate that Futhark's elimination of higher-order functions and modules leads to efficient generated code.

AB - We present a design pattern for composing deep learning networks in a typed, higher-order fashion. The exposed library functions are generically typed and the composition structure allows for networks to be trained (using backpropagation) and for trained networks to be used for predicting new results (using forward-propagation). Individual layers in a network can take different forms ranging over dense sigmoid layers to convolutional layers. The paper discusses different typing techniques aimed at enforcing proper use and composition of networks. The approach is implemented in Futhark, a data-parallel functional language and compiler targeting GPU architectures, and we demonstrate that Futhark's elimination of higher-order functions and modules leads to efficient generated code.

KW - Data-parallelism

KW - Deep learning

KW - Functional languages

UR - http://www.scopus.com/inward/record.url?scp=85072539228&partnerID=8YFLogxK

U2 - 10.1145/3331553.3342617

DO - 10.1145/3331553.3342617

M3 - Article in proceedings

SP - 47

EP - 59

BT - FHPNC 2019 - Proceedings of the 8th ACM SIGPLAN International Workshop on Functional High-Performance and Numerical Computing, co-located with ICFP 2019

A2 - Zocca, Marco

PB - Association for Computing Machinery

T2 - 8th ACM SIGPLAN International Workshop on Functional High-Performance and Numerical Computing, FHPNC 2019, co-located with ICFP 2019

Y2 - 18 August 2019

ER -

ID: 230447542