PhilSci Archive

Understanding and Deep Learning Representation

Tamir, Michael and Elay, Shech (2022) Understanding and Deep Learning Representation. [Preprint]

[img]
Preview
Text
PREPRINT Understanding and Deep Learning Representation.pdf

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: Preprint
Creators:
CreatorsEmailORCID
Tamir, Michaelmike.tamir@berkeley.edu0000-0002-2011-6137
Elay, Shechezs0038@auburn.edu0000-0002-3863-5058
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: 11 Nov 2022 14:44
Last Modified: 11 Nov 2022 14:44
Item ID: 21377
Subjects: Specific Sciences > Artificial Intelligence
Specific Sciences > Cognitive Science > Concepts and Representations
Specific Sciences > Artificial Intelligence > Machine Learning
Date: 2022
URI: http://philsci-archive.pitt.edu/id/eprint/21377

Monthly Views for the past 3 years

Monthly Downloads for the past 3 years

Plum Analytics

Actions (login required)

View Item View Item