Machine understanding and deep learning representation
Open Access
- 30 January 2023
- journal article
- research article
- Published by Springer Nature in Synthese
- Vol. 201 (2) , 1-27
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 the 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 persons, 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.Keywords
This publication has 39 references indexed in Scilit:
- Anthropomorphism: Opportunities and Challenges in Human–Robot InteractionInternational Journal of Social Robotics, 2014
- Scientific understanding: truth or dare?Synthese, 2014
- Types of understanding: Their nature and their relation to knowledgeConceptus, 2014
- No understanding without explanationStudies in History and Philosophy of Science, 2013
- Representation Learning: A Review and New PerspectivesIEEE Transactions on Pattern Analysis and Machine Intelligence, 2013
- A few useful things to know about machine learningCommunications of the ACM, 2012
- Understanding as representation manipulabilitySynthese, 2011
- Learning Deep Architectures for AIFoundations and Trends in Machine Learning, 2009
- A Contextual Approach to Scientific UnderstandingSynthese, 2005
- Understanding: Art and scienceSynthese, 1993