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

. 2018 Jul 13;8:10636. doi: 10.1038/s41598-018-28865-1

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

© The Author(s) 2018

Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as 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 images or other third party material in this article are included in the article’s Creative Commons license, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons license and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this license, visit http://creativecommons.org/licenses/by/4.0/.

PMC Copyright notice

(a) Relationship between high-level visual information and semantic features in the attractor network model. The five semantic feature units with the highest learned connection weights to visual nodes are made of fabric/cloth/material, is circular/round, made of plastic, made of metal, and is green. For each semantic feature, the visual node (grey circle) with the strongest connection weight (green text) is shown. For each visual node, we display 12 of the 16 images with the highest values for that node. Also shown for each node are other semantic features with connection weights > 10. Different visual nodes reflect different high-level visual regularities in images which are mapped on to semantic features in meaningful ways (roundness, greenness, thinness, etc). (b) Semantic features which are most strongly activated by object images. For each semantic feature unit in the attractor model, we find the maximum input activation to that feature node from all visual input images. Six semantic features with high maximal input are shown, and the first image in each row is the features’ maximally activating image. The seven next most strongly activating images for each feature are also shown, as is the sharedness of each feature (i.e. the number of concepts the feature occurs in). Object images reprinted with permission from Hemera Photo Objects.