Figure - PMC

Skip to main content

An official website of the United States government

Here's how you know

Here's how you know

Official websites use .gov
A .gov website belongs to an official government organization in the United States.

Secure .gov websites use HTTPS
A lock ( ) or https:// means you've safely connected to the .gov website. Share sensitive information only on official, secure websites.

View full-text article in PMC

. 2016 Jan 11;17(Suppl 1):9. doi: 10.1186/s12859-015-0852-1

Search in PMC
Search in PubMed
View in NLM Catalog
Add to search

© Chen et al. 2015

Open AccessThis article is distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution, and reproduction in any medium, provided you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license, and indicate if changes were made. The Creative Commons Public Domain Dedication waiver (http://creativecommons.org/publicdomain/zero/1.0/) applies to the data made available in this article, unless otherwise stated.

PMC Copyright notice

Fig. 2 — The histogram of the expected states of hidden units (probability of hidden units to be on) in the first hidden layer for the conventional autoencoder (a) and sparse autoencoder (b) respectively. For both models, the number of hidden units from the first hidden layer to the fourth hidden layer is 214, 100, 50, and 25 respectively. The sparsity threshold for the sparse autoencoder is 0.1. A hidden unit has a state under each experiment condition. Therefore, the total number of states for all hidden units is the number of experiment condition (1609) * the number of hidden units (214). The x-axis is the probability of a hidden unit to be on ranging from 0 to 1. The y-axis is the count of states