A New Research on Machine Learning, Inductive Reasoning, Reliability of Generalisations

Petr Špelda, a member of Periculum's research project on Artificial Intelligence, just published a new paper which synthesises statistical learning theory with philosophical inquiries into the nature of representation offering new insights regarding inductive reasoning and reliability of generalisations.
Date: 21/8/2018 Author: Petr Špelda Vít Střítecký

Špelda, Petr (2018): Machine learning, inductive reasoning, and reliability of generalisations. AI & SOCIETY, forthcoming. 10.1007/s00146-018-0860-6.

The present paper shows how statistical learning theory and machine learning models can be used to enhance understanding of AI-related epistemological issues regarding inductive reasoning and reliability of generalisations. Towards this aim, the paper proceeds as follows. First, it expounds Price’s dual image of representation in terms of the notions of e-representations and i-representations that constitute subject naturalism. For Price, this is not a strictly anti-representationalist position but rather a dualist one (e– and i-representations). Second, the paper links this debate with machine learning in terms of statistical learning theory becoming more viable epistemological tool when it abandons the perspective of object naturalism. The paper then argues that machine learning grounds a form of knowing that can be understood in terms of e– and i-representation learning. Third, this synthesis shows a way of analysing inductive reasoning in terms of reliability of generalisations stemming from a structure of e– and i-representations. In the age of Artificial Intelligence, connecting Price’s dual view of representation with Deep Learning provides an epistemological way forward and even perhaps an approach to how knowing is possible.


Read the paper here: Machine Learning, Inductive Reasoning, Reliability of Generalisations