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

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


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.



    Upload a copy of this work     Papers currently archived: 92,369

External links

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

Through your library

Similar books and articles

The Equals, the Equals Themselves, Equality, and the Equals Itself.Francesco Ademollo - 2007 - Documenti E Studi Sulla Tradizione Filosofica Medievale 18:1-20.
Understanding Deep Learning with Statistical Relevance.Tim Räz - 2022 - Philosophy of Science 89 (1):20-41.
What Relational Egalitarians Should (Not) Believe.Andreas Bengtson & Lauritz Aastrup Munch - 2024 - Journal of Ethics and Social Philosophy 27 (2).
Deep gunk and deep junk.Daniel Giberman - 2021 - Synthese 199 (3-4):5645-5667.
Deep learning: A philosophical introduction.Cameron Buckner - 2019 - Philosophy Compass 14 (10):e12625.
Big Data and Deep Learning Models.Daniel Sander Hoffmann - 2022 - Principia: An International Journal of Epistemology 26 (3):597-614.
The basis of equality.Geoffrey Cupit - 2000 - Philosophy 75 (1):105-125.
Doxastic Affirmative Action.Andreas Bengtson & Lauritz Aastrup Munch - 2024 - Ethical Theory and Moral Practice 27 (2):203-220.


Added to PP

4 (#1,629,422)

6 months
4 (#798,692)

Historical graph of downloads
How can I increase my downloads?

Author's Profile

Citations of this work

No citations found.

Add more citations