Write a Blog >>
ICFP 2019
Sun 18 - Fri 23 August 2019 Berlin, Germany
Sun 18 Aug 2019 13:40 - 14:03 at Reindeer - Machine Learning Chair(s): Dominic Steinitz

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 back-propagation) 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.

Sun 18 Aug

FHPNC-2019-papers
13:40 - 14:50: FHPNC - Machine Learning at Reindeer
Chair(s): Dominic SteinitzTweag I/O
FHPNC-2019-papers13:40 - 14:03
Talk
Duc Minh TranDIKU, University of Copenhagen, Troels HenriksenUniversity of Copenhagen, Denmark, Martin ElsmanUniversity of Copenhagen, Denmark
Link to publication
FHPNC-2019-papers14:03 - 14:26
Talk
FHPNC-2019-papers14:26 - 14:50
Talk
Abhiroop SarkarChalmers University of Technology, Mary Sheeran