Tamir, Michael and Elay, Shech (2023) Machine Understanding and Deep Learning Representation. Synthese, 201 (51). ISSN 1573-0964

Preview

Text Machine_Understanding_and_Deep_Learning_Representation (ForthcomingSYNTHESE20221128).pdf - Accepted Version Download (1MB) | Preview

Abstract

Practical ability manifested through robust and reliable task performance, as well as information relevance and well-structured representation, are key factors indicative of understanding in philosophical literature. We explore these factors in the context of deep learning, identifying prominent patterns in how the results of these algorithms represent information. While the estimation applications of modern neural networks do not qualify as the mental activity of minded agents, we argue that coupling analyses from philosophical accounts with the empirical and theoretical basis for identifying these factors in deep learning representations provides a framework for discussing and critically evaluating potential machine understanding given the continually improving task performance enabled by such algorithms.

---

Export/Citation:

EndNote | BibTeX | Dublin Core | ASCII/Text Citation (Chicago) | HTML Citation | OpenURL

Social Networking:

Share |

---

Item Type:	Published Article or Volume
Creators:	Creators Email ORCID Tamir, Michael mike.tamir@berkeley.edu 0000-0002-2011-6137 Elay, Shech ezs0038@auburn.edu 0000-0002-3863-5058
Keywords:	Understanding, Machine Learning, Deep Learning, Representation, Artificial Intelligence
Subjects:	Specific Sciences > Artificial Intelligence Specific Sciences > Cognitive Science > Concepts and Representations Specific Sciences > Artificial Intelligence > Machine Learning
Depositing User:	Dr Michael Tamir
Date Deposited:	31 Jan 2023 18:26
Last Modified:	31 Jan 2023 18:26
Item ID:	21482
Journal or Publication Title:	Synthese
Publisher:	Springer (Springer Science+Business Media B.V.)
Official URL:	https://link.springer.com/article/10.1007/s11229-0...
DOI or Unique Handle:	10.1007/s11229-022-03999-y
Subjects:	Specific Sciences > Artificial Intelligence Specific Sciences > Cognitive Science > Concepts and Representations Specific Sciences > Artificial Intelligence > Machine Learning
Date:	30 January 2023
Volume:	201
Number:	51
ISSN:	1573-0964
URI:	https://philsci-archive.pitt.edu/id/eprint/21482

Available Versions of this Item

• Understanding and Deep Learning Representation. (deposited 11 Nov 2022 14:44)
  • Machine Understanding and Deep Learning Representation. (deposited 31 Jan 2023 18:26) [Currently Displayed]

Monthly Views for the past 3 years

Monthly Downloads for the past 3 years

Plum Analytics

Altmetric.com

Actions (login required)

View Item