日本語
 
Help Privacy Policy ポリシー/免責事項
  詳細検索ブラウズ

アイテム詳細

登録内容を編集ファイル形式で保存
一時保存へ追加
 タグ情報を表示リリース履歴を表示詳細要約
  Deep problems with neural network models of human vision

Bowers, J. S., Malhotra, G., Dujmović, M., Montero, M. L., Tsvetkov, C., Biscione, V., Puebla, G., Adolfi, F., Hummel, J. E., Heaton, R. F., Evans, B. D., Mitchell, J., & Blything, R. (2022). Deep problems with neural network models of human vision. Behavioral and Brain Sciences, 1-74. doi:10.1017/S0140525X22002813.

Item is

 

表示: 全項目 非表示: 全項目

基本情報

表示: 非表示:
アイテムのパーマリンク: https://hdl.handle.net/21.11116/0000-000C-85BE-8 版のパーマリンク: https://hdl.handle.net/21.11116/0000-000C-85BF-7
資料種別: 学術論文

ファイル

表示: ファイル

作成者

表示:
非表示:
 作成者:
Bowers, Jeffrey S., 著者
Malhotra, Gaurav, 著者
Dujmović, Marin, 著者
Montero, Milton Llera, 著者
Tsvetkov, Christian, 著者
Biscione, Valerio, 著者
Puebla, Guillermo, 著者
Adolfi, Federico1, 2, 著者
Hummel, John E., 著者
Heaton, Rachel F., 著者
Evans, Benjamin D., 著者
Mitchell, Jeffrey, 著者
Blything, Ryan, 著者
所属:
1Ernst Strüngmann Institute (ESI) for Neuroscience in Cooperation with Max Planck Society, Max Planck Society, Deutschordenstr. 46, 60528 Frankfurt, DE, ou_2074314              
2Poeppel Lab, Ernst Strüngmann Institute (ESI) for Neuroscience in Cooperation with Max Planck Society, Max Planck Society, Deutschordenstraße 46, 60528 Frankfurt, DE, ou_3381225              

内容説明

表示:
非表示:
キーワード: Brain-Score Computational Neuroscience Deep Neural Networks Human Vision Object recognition
 要旨: Deep neural networks (DNNs) have had extraordinary successes in classifying photographic images of objects and are often described as the best models of biological vision. This conclusion is largely based on three sets of findings: (1) DNNs are more accurate than any other model in classifying images taken from various datasets, (2) DNNs do the best job in predicting the pattern of human errors in classifying objects taken from various behavioral datasets, and (3) DNNs do the best job in predicting brain signals in response to images taken from various brain datasets (e.g., single cell responses or fMRI data). However, these behavioral and brain datasets do not test hypotheses regarding what features are contributing to good predictions and we show that the predictions may be mediated by DNNs that share little overlap with biological vision. More problematically, we show that DNNs account for almost no results from psychological research. This contradicts the common claim that DNNs are good, let alone the best, models of human object recognition. We argue that theorists interested in developing biologically plausible models of human vision need to direct their attention to explaining psychological findings. More generally, theorists need to build models that explain the results of experiments that manipulate independent variables designed to test hypotheses rather than compete on making the best predictions. We conclude by briefly summarizing various promising modelling approaches that focus on psychological data.

資料詳細

表示:
非表示:
言語:
 日付: 2022-12-01
 出版の状態: オンラインで出版済み
 ページ: -
 出版情報: -
 目次: -
 査読: 査読あり
 識別子（DOI, ISBNなど）: DOI: 10.1017/S0140525X22002813
 学位: -

関連イベント

表示:

訴訟

表示:

Project information

表示:

出版物 1

表示:
非表示:
出版物名: Behavioral and Brain Sciences
種別: 学術雑誌
 著者・編者:
所属:
出版社, 出版地: -
ページ: - 巻号: - 通巻号: - 開始・終了ページ: 1 - 74 識別子（ISBN, ISSN, DOIなど）: ISSN: 0140-525X
ISSN: 1469-1825