For deep networks, the whole equals the sum of the parts

, , , &
Behavioral and Brain Sciences 46:e396 (2023)
  Copy   BIBTEX

Abstract

Deep convolutional networks exceed humans in sensitivity to local image properties, but unlike biological vision systems, do not discover and encode abstract relations that capture important properties of objects and events in the world. Coupling network architectures with additional machinery for encoding abstract relations will make deep networks better models of human abilities and more versatile and capable artificial devices.

Categories

Keywords

Reprint years

DOI

10.1017/s0140525x23001541

Links

PhilArchive



    Upload a copy of this work     Papers currently archived: 93,098

External links

Setup an account with your affiliations in order to access resources via your University's proxy server

Through your library

My notes

Similar books and articles

Fixing the problems of deep neural networks will require better training data and learning algorithms.Drew Linsley & Thomas Serre - 2023 - Behavioral and Brain Sciences 46:e400.
Psychophysics may be the game-changer for deep neural networks (DNNs) to imitate the human vision.Keerthi S. Chandran, Amrita Mukherjee Paul, Avijit Paul & Kuntal Ghosh - 2023 - Behavioral and Brain Sciences 46:e388.
Computational Functionalism for the Deep Learning Era.Ezequiel López-Rubio - 2018 - Minds and Machines 28 (4):667-688.
Toward biologically plausible artificial vision.Mason Westfall - 2023 - Behavioral and Brain Sciences 46:e290.
Neural networks need real-world behavior.Aedan Y. Li & Marieke Mur - 2023 - Behavioral and Brain Sciences 46:e398.
On the Opacity of Deep Neural Networks.Anders Søgaard - forthcoming - Canadian Journal of Philosophy:1-16.
Structural-parametric synthesis of deep learning neural networks.Sineglazov V. M. & Chumachenko O. I. - 2020 - Artificial Intelligence Scientific Journal 25 (4):42-51.
Deep problems with neural network models of human vision.Jeffrey S. Bowers, Gaurav Malhotra, Marin Dujmović, Milton Llera Montero, Christian Tsvetkov, Valerio Biscione, Guillermo Puebla, Federico Adolfi, John E. Hummel, Rachel F. Heaton, Benjamin D. Evans, Jeffrey Mitchell & Ryan Blything - 2023 - Behavioral and Brain Sciences 46:e385.
Deep neural networks are not a single hypothesis but a language for expressing computational hypotheses.Tal Golan, JohnMark Taylor, Heiko Schütt, Benjamin Peters, Rowan P. Sommers, Katja Seeliger, Adrien Doerig, Paul Linton, Talia Konkle, Marcel van Gerven, Konrad Kording, Blake Richards, Tim C. Kietzmann, Grace W. Lindsay & Nikolaus Kriegeskorte - 2023 - Behavioral and Brain Sciences 46:e392.
Meaning maps and saliency models based on deep convolutional neural networks are insensitive to image meaning when predicting human fixations.Marek A. Pedziwiatr, Matthias Kümmerer, Thomas S. A. Wallis, Matthias Bethge & Christoph Teufel - 2021 - Cognition 206 (C):104465.

Analytics

Added to PP
2023-12-08

Downloads
4 (#1,644,260)

6 months
4 (#862,833)

Historical graph of downloads
How can I increase my downloads?

Author's Profile

Citations of this work

No citations found.

Add more citations

References found in this work

Add more references