Semantic Relatedness Emerges in Deep Convolutional Neural Networks Designed for Object Recognition

Semantic Relatedness Emerges in Deep Convolutional Neural Networks Designed for Object Recognition

Human not only can effortlessly recognize objects, but also characterize object categories into semantic concepts with a nested hierarchical structure. One dominant view is that top-down conceptual guidance is necessary to form such hierarchy. Here we challenged this idea by examining whether deep c...

Full description

Bibliographic Details
Main Authors: Taicheng Huang, Zonglei Zhen, Jia Liu
Format: Article
Language:English
Published: Frontiers Media S.A. 2021-02-01
Series:Frontiers in Computational Neuroscience
Subjects:
deep convolutional neural network
semantic relatedness
WordNet
perceptual experience
conceptual guidance
Online Access:https://www.frontiersin.org/articles/10.3389/fncom.2021.625804/full

Internet

https://www.frontiersin.org/articles/10.3389/fncom.2021.625804/full

Similar Items