Creel, Kathleen A. (2019) Transparency in Complex Computational Systems. [Preprint]

Preview

Text Creel_TransparencyInComplexComputationalSystems.pdf Download (239kB) | Preview

Abstract

Scientists depend on complex computational systems that are often ineliminably opaque, to the detriment of our ability to give scientific explanations and detect artifacts. Some philosophers have suggested treating opaque systems instrumentally, but computer scientists developing strategies for increasing transparency are correct in finding this unsatisfying. Instead, I propose an analysis of transparency as having three forms: transparency of the algorithm, the realization of the algorithm in code, and the way that code is run on particular hardware and data. This targets the transparency most useful for a task, avoiding instrumentalism by providing partial transparency when full transparency is impossible.

---

Export/Citation:

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

Social Networking:

Share |

---

Item Type:	Preprint
Creators:	Creators Email ORCID Creel, Kathleen A. kac284@pitt.edu 0000-0001-7371-2680
Additional Information:	forthcoming in Philosophy of Science
Keywords:	Transparency, Opacity, Machine Learning, Simulation, Computation, Explanation
Subjects:	Specific Sciences > Computer Science General Issues > Computer Simulation General Issues > Explanation Specific Sciences > Artificial Intelligence > Machine Learning
Depositing User:	Kathleen A. Creel
Date Deposited:	29 Nov 2019 05:41
Last Modified:	29 Nov 2019 05:41
Item ID:	16669
Subjects:	Specific Sciences > Computer Science General Issues > Computer Simulation General Issues > Explanation Specific Sciences > Artificial Intelligence > Machine Learning
Date:	28 November 2019
URI:	https://philsci-archive.pitt.edu/id/eprint/16669

Monthly Views for the past 3 years

Monthly Downloads for the past 3 years

Plum Analytics

Actions (login required)

View Item