Autoencoder Node Saliency

RESOURCE

Abstract

Autoencoder node saliency (ANS) is a novel method intended to explain the lenrning tasks perfonned in the hidden layer of an autoencoder. ANS ranks the hidden nodes based on their ability to perfonn a given learning task. It identifies the hidden node that best distinguishes between two classes of data points. The weights from the identified hidden nodes correspond to original features that contribute to the data differentiation.
Developers:
Fan, Ya [1]
  1. Lawrence Livermore National Lab. (LLNL), Livermore, CA (United States)
Release Date:
2017-11-21
Project Type:
Open Source, Publicly Available Repository
Software Type:
Scientific
Licenses:
MIT License
Sponsoring Org.:
Code ID:
16356
Site Accession Number:
LLNL-CODE-753346
Research Org.:
Lawrence Livermore National Laboratory (LLNL), Livermore, CA (United States)
Country of Origin:
United States

RESOURCE

Citation Formats

Fan, Ya J. Autoencoder Node Saliency. Computer Software. https://github.com/LLNL/ANS. USDOE National Nuclear Security Administration (NNSA). 21 Nov. 2017. Web. doi:10.11578/dc.20180731.9.
Fan, Ya J. (2017, November 21). Autoencoder Node Saliency. [Computer software]. https://github.com/LLNL/ANS. https://doi.org/10.11578/dc.20180731.9.
Fan, Ya J. "Autoencoder Node Saliency." Computer software. November 21, 2017. https://github.com/LLNL/ANS. https://doi.org/10.11578/dc.20180731.9.
@misc{ doecode_16356,
title = {Autoencoder Node Saliency},
author = {Fan, Ya J.},
abstractNote = {Autoencoder node saliency (ANS) is a novel method intended to explain the lenrning tasks perfonned in the hidden layer of an autoencoder. ANS ranks the hidden nodes based on their ability to perfonn a given learning task. It identifies the hidden node that best distinguishes between two classes of data points. The weights from the identified hidden nodes correspond to original features that contribute to the data differentiation.},
doi = {10.11578/dc.20180731.9},
url = {https://doi.org/10.11578/dc.20180731.9},
howpublished = {[Computer Software] \url{https://doi.org/10.11578/dc.20180731.9}},
year = {2017},
month = {nov}
}