論文

査読有り 国際誌
2019年2月12日

Characterization of deep neural network features by decodability from human brain activity.

Scientific data
  • Tomoyasu Horikawa
  • ,
  • Shuntaro C Aoki
  • ,
  • Mitsuaki Tsukamoto
  • ,
  • Yukiyasu Kamitani

6
開始ページ
190012
終了ページ
190012
記述言語
英語
掲載種別
DOI
10.1038/sdata.2019.12
出版者・発行元
Springer Nature

Achievements of near human-level performance in object recognition by deep neural networks (DNNs) have triggered a flood of comparative studies between the brain and DNNs. Using a DNN as a proxy for hierarchical visual representations, our recent study found that human brain activity patterns measured by functional magnetic resonance imaging (fMRI) can be decoded (translated) into DNN feature values given the same inputs. However, not all DNN features are equally decoded, indicating a gap between the DNN and human vision. Here, we present a dataset derived from DNN feature decoding analyses, which includes fMRI signals of five human subjects during image viewing, decoded feature values of DNNs (AlexNet and VGG19), and decoding accuracies of individual DNN features with their rankings. The decoding accuracies of individual features were highly correlated between subjects, suggesting the systematic differences between the brain and DNNs. We hope the present dataset will contribute to revealing the gap between the brain and DNNs and provide an opportunity to make use of the decoded features for further applications.

リンク情報
DOI
https://doi.org/10.1038/sdata.2019.12
PubMed
https://www.ncbi.nlm.nih.gov/pubmed/30747910
PubMed Central
https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6371890
URL
http://orcid.org/0000-0002-6384-8098
ID情報
  • DOI : 10.1038/sdata.2019.12
  • ISSN : 2052-4463
  • ORCIDのPut Code : 55069287
  • PubMed ID : 30747910
  • PubMed Central 記事ID : PMC6371890

エクスポート
BibTeX RIS