PhilSci Archive

Deep Learning as Method-Learning: Pragmatic Understanding, Epistemic Strategies and Design-Rules

Kieval, Phillip Hintikka and Westerblad, Oscar (2024) Deep Learning as Method-Learning: Pragmatic Understanding, Epistemic Strategies and Design-Rules. In: UNSPECIFIED.

[img]
Preview
Text
Deep Learning as Method-Learning PSA2024 Preprint.pdf

Download (116kB) | Preview

Abstract

We claim that scientists working with deep learning (DL) models exhibit a form of pragmatic understanding that is not reducible to or dependent on explanation. This pragmatic understanding comprises a set of learned methodological principles that underlie DL model design-choices and secure their reliability. We illustrate this action-oriented pragmatic understanding with a case study of AlphaFold2, highlighting the interplay between background knowledge of a problem and methodological choices involving techniques for constraining how a model learns from data. Building successful models requires pragmatic understanding to apply modelling strategies that encourage the model to learn data patterns that will facilitate reliable generalisation.


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

Item Type: Conference or Workshop Item (UNSPECIFIED)
Creators:
CreatorsEmailORCID
Kieval, Phillip Hintikkapzhk2@cam.ac.uk
Westerblad, Oscarow259@cam.ac.uk
Keywords: deep learning; understanding; pragmatic understanding; AlphaFold; method learning
Subjects: General Issues > Data
Specific Sciences > Biology > Molecular Biology/Genetics
Specific Sciences > Computer Science
Specific Sciences > Artificial Intelligence
General Issues > Computer Simulation
General Issues > Explanation
Specific Sciences > Artificial Intelligence > Machine Learning
General Issues > Models and Idealization
Depositing User: Phillip Hintikka Kieval
Date Deposited: 28 May 2024 15:13
Last Modified: 28 May 2024 15:13
Item ID: 23489
Subjects: General Issues > Data
Specific Sciences > Biology > Molecular Biology/Genetics
Specific Sciences > Computer Science
Specific Sciences > Artificial Intelligence
General Issues > Computer Simulation
General Issues > Explanation
Specific Sciences > Artificial Intelligence > Machine Learning
General Issues > Models and Idealization
Date: 2024
URI: https://philsci-archive.pitt.edu/id/eprint/23489

Monthly Views for the past 3 years

Monthly Downloads for the past 3 years

Plum Analytics

Actions (login required)

View Item View Item