Kieval, Phillip H. (2026) Deep Neural Networks, Architectural Constraints, and Scientific Representation. In: UNSPECIFIED.

Text Deep_Neural_Networks_and_Scientific_Representation_PSA2026_3_9_26.pdf Download (232kB)

Abstract

I argue that the practice of applying generic deep neural network (DNN) architectures with minimal theoretical constraints falls short of the conditions required for scientific representation on both substantive or deflationary accounts. Substantive views fail because the characteristic interpretive activities that establish representation relations are absent from generic DNN practice. Deflationary views fare better but risk trivializing the concept of surrogative inference when applied to generic DNNs. I then propose that theoretically-motivated architectural constraints function as a form of indirect characterization that grounds deflationary scientific representation.

---

Export/Citation:

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

Social Networking:

Share |

---

Item Type:	Conference or Workshop Item (UNSPECIFIED)
Creators:	Creators Email ORCID Kieval, Phillip H. pkieval@ufl.edu 0000-0001-5369-0322
Subjects:	Specific Sciences > Artificial Intelligence > Machine Learning General Issues > Models and Idealization
Depositing User:	Phillip Hintikka Kieval
Date Deposited:	12 Jun 2026 12:36
Last Modified:	12 Jun 2026 12:36
Item ID:	30072
Subjects:	Specific Sciences > Artificial Intelligence > Machine Learning General Issues > Models and Idealization
Date:	2026
URI:	https://philsci-archive.pitt.edu/id/eprint/30072

Monthly Views for the past 3 years

Monthly Downloads for the past 3 years

Plum Analytics

Actions (login required)

View Item