Inference of abstraction for human-like probabilistic reasoning

Kido, Hiroyuki ORCID: https://orcid.org/0000-0002-7622-4428 2025. Inference of abstraction for human-like probabilistic reasoning. Presented at: 4th Advanced Course and Symposium on Artificial Intelligence & Neuroscience (ACAIN), Tuscany, Italy, 22-25 September 2024. Published in: Nicosia, Giuseppe, Ojha, Varun, Giesselbach, Sven, Panos Pardalos, M. and Umeton, Renato eds. Machine Learning, Optimization, and Data Science. Lecture Notes in Computer Science (15510) Springer Cham, pp. 191-206. 10.1007/978-3-031-82487-6_9

Preview

PDF - Accepted Post-Print Version Download (2MB) | Preview

Abstract

We propose a conceptually new approach to unify symbolic reasoning and probabilistic reasoning, both core aspects of human higher-order cognitive function. The key underlying idea is inference of abstraction, or selective ignorance, in which abstract symbolic knowledge is derived directly from concrete data via models in formal logic. We compare this simple idea with the semantics of Bayesian networks and show that our idea does not need the assumption of independence or conditional independence of symbolic knowledge, an unrealistic but necessary assumption of Bayesian networks and their variants. We also show that, in the machine learning context, the idea can be seen as an all-neighbour method, which is a further generalisation of an all-nearest neighbour method, itself a generalisation of the k-nearest neighbour method. We use the MNIST dataset to empirically justify the theoretical advantage of the idea.

Item Type:	Conference or Workshop Item (Paper)
Date Type:	Publication
Status:	Published
Schools:	Schools > Computer Science & Informatics
Publisher:	Springer Cham
ISBN:	9783031824869
Date of First Compliant Deposit:	26 June 2024
Date of Acceptance:	1 June 2024
Last Modified:	09 Apr 2025 11:40
URI:	https://orca.cardiff.ac.uk/id/eprint/170136

Actions (repository staff only)

Edit Item