Deep Convolutional Neural Networks Outperform Feature-Based But Not Categorical Models in Explaining Object Similarity Judgments

Deep Convolutional Neural Networks Outperform Feature-Based But Not Categorical Models in Explaining Object Similarity Judgments

Recent advances in Deep convolutional Neural Networks (DNNs) have enabled unprecedentedly accurate computational models of brain representations, and present an exciting opportunity to model diverse cognitive functions. State-of-the-art DNNs achieve human-level performance on object categorisation,...

Full description

Bibliographic Details
Main Authors: Kamila M. Jozwik, Nikolaus Kriegeskorte, Katherine R. Storrs, Marieke Mur
Format: Article
Language:English
Published: Frontiers Media S.A. 2017-10-01
Series:Frontiers in Psychology
Subjects:
object recognition
similarity judgments
deep neural networks
categories
features
weighted representational modeling
Online Access:http://journal.frontiersin.org/article/10.3389/fpsyg.2017.01726/full

Internet

http://journal.frontiersin.org/article/10.3389/fpsyg.2017.01726/full

Similar Items