PhilSci Archive

Understanding from Deep Learning Models in Context

Shech, Elay and Tamir, Michael (2023) Understanding from Deep Learning Models in Context. [Preprint]

[img]
Preview
Text
FINAL - Understanding from Deep Learning Models in Context.pdf

Download (394kB) | Preview

Abstract

This paper places into context how the term model in machine learning (ML) contrasts with traditional usages of scientific models for understanding and we show how direct analysis of an estimator’s learned transformations (specifically, the hidden layers of a deep learning model) can improve understanding of the target phenomenon and reveal how the model organizes relevant information. Specifically, three modes of understanding will be identified, the difference between implementation irrelevance and functionally approximate irrelevance will be disambiguated, and how this distinction impacts potential understanding with these models will be explored. Additionally, by distinguishing between empirical link failures from representational ones, an ambiguity in the concept of link uncertainty will be addressed thus clarifying the role played by scientific background knowledge in enabling understanding with ML.


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

Item Type: Preprint
Creators:
CreatorsEmailORCID
Shech, Elayeshech@gmail.com
Tamir, Michaelmntamir@gmail.com
Keywords: Machine Learning; Deep Learning; Models; Understanding
Subjects: General Issues > Explanation
Specific Sciences > Artificial Intelligence > Machine Learning
General Issues > Models and Idealization
Depositing User: Dr. Elay Shech
Date Deposited: 21 Oct 2022 18:31
Last Modified: 21 Oct 2022 18:31
Item ID: 21296
Subjects: General Issues > Explanation
Specific Sciences > Artificial Intelligence > Machine Learning
General Issues > Models and Idealization
Date: 2023
URI: https://philsci-archive.pitt.edu/id/eprint/21296

Monthly Views for the past 3 years

Monthly Downloads for the past 3 years

Plum Analytics

Actions (login required)

View Item View Item