Repository logo
 

Improving Interpretability and Regularisation in Deep Learning

Repository URI

https://www.repository.cam.ac.uk/handle/1810/271781

Repository DOI

https://doi.org/10.17863/CAM.18408
Thumbnail Image

Files

TASLP2774919.tar.gz (3.1 MB)

Type

Dataset

Change log

Authors

Wu, Chunyang  ORCID logo  https://orcid.org/0000-0002-0269-3555
Gales, Mark  ORCID logo  https://orcid.org/0000-0002-5311-8219

Description

The provided .ctm and scoring .sys files correspond to the MPE systems of Table VI (Javanese) and Table X (BN) of this paper.

Version

Software / Usage instructions

HTK Toolkit, NIST SCLITE Scoring Package

Keywords

activation regularisation, interpretability, visualisation, neural network, deep learning

Publisher

Rights and licensing

Attribution 4.0 International (CC BY 4.0)
Except where otherwised noted, this item's license is described as Attribution 4.0 International (CC BY 4.0)
Sponsorship
IARPA (4912046943)
EPSRC (via University of Edinburgh) (EP/I031022/1 ERI016379)

Relationships

Supplements:
https://doi.org/10.1109/TASLP.2017.2774919

Collections

Research Data - Engineering