PhilSci Archive

The Importance of Understanding Deep Learning

Räz, Tim and Beisbart, Claus (2022) The Importance of Understanding Deep Learning. Erkenntnis. ISSN 0165-0106

[img]
Preview
Text
s10670-022-00605-y.pdf - Published Version
Available under License Creative Commons Attribution.

Download (836kB) | Preview

Abstract

Some machine learning models, in particular deep neural networks (DNNs), are not very well understood; nevertheless, they are frequently used in science. Does this lack of understanding pose a problem for using DNNs to understand empirical phenomena? Emily Sullivan has recently argued that understanding with DNNs is not limited by our lack of understanding of DNNs themselves. In the present paper, we will argue, contra Sullivan, that our current lack of understanding of DNNs does limit our ability to understand with DNNs. Sullivan’s claim hinges on which notion of understanding is at play. If we employ a weak notion of understanding, then her claim is tenable, but rather weak. If, however, we employ a strong notion of understanding, particularly explanatory understanding, then her claim is not tenable.


Export/Citation: EndNote | BibTeX | Dublin Core | ASCII/Text Citation (Chicago) | HTML Citation | OpenURL
Social Networking:
Share |

Item Type: Published Article or Volume
Creators:
CreatorsEmailORCID
Räz, Timtim.raez@gmail.com
Beisbart, ClausClaus.Beisbart@philo.unibe.ch
Additional Information: This article is licensed under a Creative Commons Attribution 4.0 International License, https://creativecommons.org/licenses/by/4.0/
Subjects: Specific Sciences > Computer Science
General Issues > Explanation
Specific Sciences > Artificial Intelligence > Machine Learning
Depositing User: Tim Räz
Date Deposited: 26 Oct 2022 14:57
Last Modified: 26 Oct 2022 14:57
Item ID: 21314
Journal or Publication Title: Erkenntnis
Publisher: Springer (Springer Science+Business Media B.V.)
Official URL: https://link.springer.com/article/10.1007/s10670-0...
DOI or Unique Handle: https://doi.org/10.1007/s10670-022-00605-y
Subjects: Specific Sciences > Computer Science
General Issues > Explanation
Specific Sciences > Artificial Intelligence > Machine Learning
Date: 7 August 2022
ISSN: 0165-0106
URI: https://philsci-archive.pitt.edu/id/eprint/21314

Monthly Views for the past 3 years

Monthly Downloads for the past 3 years

Plum Analytics

Altmetric.com

Actions (login required)

View Item View Item