.png){kind=icon}
Return
Autoencoder node saliency: Selecting relevant latent representations
.png){kind=icon}
OA
AI
DOI：10.1016/j.patcog.2018.12.015.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
The autoencoder is an artificial neural network that performs nonlinear dimension reduction and learns hidden representations of unlabeled data. With a linear transfer function it is similar to the principal component analysis (PCA). While both methods use weight vectors for linear transformations, the autoencoder does not come with any indication similar to the eigenvalues in PCA that are paired with eigenvectors. We propose a novel autoencoder node saliency method that examines whether the features constructed by autoencoders exhibit properties related to known class labels. The supervised node saliency ranks the nodes based on their capability of performing a learning task. It is coupled with the normalized entropy difference (NED). We establish a property for NED values to verify classifying behaviors among the top ranked nodes. By applying our methods to real datasets, we demonstrate their ability to provide indications on the performing nodes and explain the learned tasks in autoencoders. (C) 2018 Elsevier Ltd. All rights reserved.
Keywords:
Autoencoder
Latent representations
Unsupervised learning
Neural networks
Node selection
Model interpretation
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
7.6
Papers:
1.3W
Citations:
4.5W
Organization
Cited Papers
ShareSaveShareSave
ShareSaveAn efficient semi-supervised representatives feature selection algorithm based on information theory.png)
PATTERN RECOGNITION
PATTERN RECOGNITIONIF7.6
PREAI
ShareSaveShareSaveShareSaveShareSaveShareSave
View more