χONN · Hub
Ontology Neural Network.
ONN learns a latent state carrying explicit ontology structure; ORTSF closes the loop with delay-robust control on top of that topology. This hub collects the working definitions, the mathematical commitments, and every manuscript in the thread.
Suggested reading order
- 01Track overview
- 02ONN + ORTSF framework paper
- 03Integrated architecture
- 04Extensions & theorems as needed
Track overview
The high-level research-track page — what ONN is, why it matters, and where it sits in the broader programme.
Canonical specifications
The authoritative formal statement of the ONN architecture and the ORTSF operator family.
Research roadmap & status
Dated notes tracking what is settled, what is under active development, and the open problems on the critical path.
Integration & north-star
ONN as one half of the unified cognitive-reasoning architecture. The integrated-architecture note sits in Part 0 because it binds SCC and ONN together.
Mathematical results
Theorems and proofs specific to ONN — topology preservation, cohomological stability, and the delay-robust feedback bound. Individual proof pages will appear here as they are written.
- Draft
ONN · mathematical results
Individual theorem pages will appear here as proofs are formalised.
Essays & working notes
Exploratory documents, working notes, and essay-form writing in the ONN thread.
Manuscripts
Every ONN-track paper — published, accepted, or in preprint.
- published · 2026 · International Journal of Topology (MDPI), 3(2), 9
Ontology Neural Network and ORTSF: A Framework for Topological Reasoning and Delay-Robust Control
The advancement of autonomous robotic systems has led to significant capabilities in perception, localization, mapping, and control, yet a critical challenge remains in representing and preserving relational semantics, c
- preprint · 2025
Advanced Topology-Preserving Neural Networks: An Extension of ONN/ORTSF Framework with Dynamic Structural Optimization
This work presents the first comprehensive empirical investigation into the practical realization of performance bounds theoretically established by the Ontology Neural Network (ONN) and Ontological Real-Time Semantic Fa
- preprint · 2025
Constructive Lyapunov Functions via Topology-Preserving Neural Networks
We present a constructive solution to the Lyapunov–Massera–Kurzweil problem via Ontology Neural Networks (ONN), bridging a 60-year gap between existence and construction in stability theory. While Massera (1949) proved t
- preprint · 2025
Ontology Neural Networks for Topologically Conditioned Constraint Satisfaction
Neuro-symbolic reasoning systems face fundamental challenges in maintaining semantic coherence while satisfying physical and logical constraints. Building upon our previous work on Ontology Neural Networks, we present an