19075

Compositional Deep Learning in Futhark

Duc Minh Tran, Troels Henriksen, Martin Elsman
University of Copenhagen, Denmark
8th ACM SIGPLAN International Workshop on Functional High-Performance and Numerical Computing (FHPNC ’19), 2019

@article{tran2019compositional,

   title={Compositional Deep Learning in Futhark},

   author={Tran, Duc Minh and Henriksen, Troels and Elsman, Martin},

   year={2019}

}

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.
Rating: 5.0/5. From 1 vote.
Please wait...

* * *

* * *

HGPU group © 2010-2019 hgpu.org

All rights belong to the respective authors

Contact us: