![[2402.08646] Inference of Abstraction for a Unified Account of Symbolic Reasoning from Data](https://arxiv.org/static/browse/0.3.4/images/arxiv-logo-fb.png){kind=logo}
[2402.08646] Inference of Abstraction for a Unified Account of Symbolic Reasoning from Data
Summary
This paper presents a unified probabilistic framework for symbolic reasoning, drawing inspiration from neuroscience, and aims to enhance understanding of human-like machine intelligence.
Why It Matters
The research offers a novel perspective on symbolic reasoning by integrating concepts from neuroscience and formal logic. This could lead to advancements in artificial intelligence, particularly in developing systems that mimic human reasoning capabilities, which is crucial for the evolution of intelligent agents.
Key Takeaways
- Introduces a probabilistic account of symbolic reasoning.
- Utilizes concepts from neuroscience to inform AI development.
- Explores formal logic to enhance understanding of reasoning processes.
- Aims to bridge the gap between data-driven approaches and human-like reasoning.
- Highlights implications for future AI systems and their intelligence.
Computer Science > Artificial Intelligence arXiv:2402.08646 (cs) [Submitted on 13 Feb 2024 (v1), last revised 23 Feb 2026 (this version, v2)] Title:Inference of Abstraction for a Unified Account of Symbolic Reasoning from Data Authors:Hiroyuki Kido View a PDF of the paper titled Inference of Abstraction for a Unified Account of Symbolic Reasoning from Data, by Hiroyuki Kido View PDF HTML (experimental) Abstract:Inspired by empirical work in neuroscience for Bayesian approaches to brain function, we give a unified probabilistic account of various types of symbolic reasoning from data. We characterise them in terms of formal logic using the classical consequence relation, an empirical consequence relation, maximal consistent sets, maximal possible sets and maximum likelihood estimation. The theory gives new insights into reasoning towards human-like machine intelligence. Subjects: Artificial Intelligence (cs.AI) Cite as: arXiv:2402.08646 [cs.AI] (or arXiv:2402.08646v2 [cs.AI] for this version) https://doi.org/10.48550/arXiv.2402.08646 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Hiroyuki Kido [view email] [v1] Tue, 13 Feb 2024 18:24:23 UTC (1,382 KB) [v2] Mon, 23 Feb 2026 12:10:05 UTC (751 KB) Full-text links: Access Paper: View a PDF of the paper titled Inference of Abstraction for a Unified Account of Symbolic Reasoning from Data, by Hiroyuki KidoView PDFHTML (experimental)TeX Source view license Current browse context: cs.AI < prev | ...
