Skip to main content
U.S. Department of Energy
Office of Scientific and Technical Information

Autoencoder Node Saliency

Software ·
DOI:https://doi.org/10.11578/dc.20180731.9· OSTI ID:code-16356 · Code ID:16356
 [1]
  1. Lawrence Livermore National Lab. (LLNL), Livermore, CA (United States)
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.
Short Name / Acronym:
ANS
Site Accession Number:
LLNL-CODE-753346
Software Type:
Scientific
License(s):
MIT License
Research Organization:
Lawrence Livermore National Laboratory (LLNL), Livermore, CA (United States)
Sponsoring Organization:
USDOE National Nuclear Security Administration (NNSA)

Primary Award/Contract Number:
AC52-07NA27344
DOE Contract Number:
AC52-07NA27344
Code ID:
16356
OSTI ID:
code-16356
Country of Origin:
United States

Similar Records

Autoencoder node saliency: Selecting relevant latent representations
Journal Article · Sun Dec 16 23:00:00 EST 2018 · Pattern Recognition · OSTI ID:1491664

Data Visualization Saliency v. 1.0
Software · Wed Sep 20 20:00:00 EDT 2017 · OSTI ID:code-23809

Efficent XAI Information Saliency Tool
Software · Mon Oct 21 20:00:00 EDT 2019 · OSTI ID:code-35964

Related Subjects