Probabilistic Extension of Neuro-Symbolic AGI Robots based on Belnap's Typed Intensional FOL
Quick Answer
This paper enhances neuro-symbolic AI using Belnap's Typed Intensional First-Order Logic ($IFOL_B$) by integrating probabilistic computations for unknown sentences.
Quick Take
This paper enhances neuro-symbolic AI using Belnap's Typed Intensional First-Order Logic ($IFOL_B$) by integrating probabilistic computations for unknown sentences. It introduces a global symmetry transformation for knowledge preservation and a local transformation for real-time decision-making, leveraging neural networks to compute probability density functions based on Shannon's maximum information entropy.
Key Points
- Expands cognitive capabilities of $IFOL_B$ with probabilistic reasoning.
- Introduces global and local symmetry transformations for knowledge and decision-making.
- Utilizes neural networks to compute probability density functions.
- Addresses limitations of purely neural systems like interpretability.
- Enhances real-time decision-making for specific subproblems.
Paper Resources
📖 Reader Mode
~2 min readAbstract:Neuro-symbolic AI based on $IFOL_B$ is a way to combine neural learning and symbolic reasoning to overcome limitations of purely neural systems (like lack of interpretability and logical structure) with formal logical machinery for self-reference. In this paper we expand the cognitive power of $IFOL_B$ by using the probability computation for the currently unknown sentences, based on Nilsson's probability structure for the $IFOL_B$. We introduce the global symmetry transformation that preserves the current knowledge database and logical deduction, and the local one used for real-time decisions about concrete (sub)problems that involve only a very strict subset of $IFOL_B$ predicates. The computation of probability density function $KI$ in both cases, based on the Shannon's maximum information entropy, is provided by neural networks of this probabilistic neuro-symbolic AGI.
| Comments: | 32 pages |
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2607.13073 [cs.AI] |
| (or arXiv:2607.13073v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2607.13073 arXiv-issued DOI via DataCite |
Submission history
From: Zoran Majkic [view email]
[v1]
Sun, 12 Jul 2026 15:54:58 UTC (49 KB)
— Originally published at arxiv.org
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.AI
See more →Automatic Ordinary Differential Equations Discovery For Biological Systems Using Large Language Model Powered Agentic System
The MEDA system utilizes large language models and symbolic regression to autonomously discover ordinary differential equations for biological systems, achieving strong structural recovery and biologically plausible models. It outperforms existing methods by integrating domain knowledge and mechanistic constraints, demonstrating effective retrieval and extrapolation capabilities.