This paper develops a formal semantic framework for Kolmogorov-Arnold Network (KAN) representations of operational games. Theoretical results establish conditions for representation adequacy, computational tractability, and semantic preservation under aggregation operations.
This research advances how AI systems learn, reason, and solve problems — with direct implications for software, automation, and scientific discovery.
Read the full paper
Access the original peer-reviewed research via OpenAlex.
| Category | 🤖 Artificial Intelligence |
| Published | Apr 13, 2025 |
| Journal | Zenodo (CERN European Organization for Nuclear Research) |
| Authors | Zhukov, Georgy Alexandrovich |
| DOI | 10.5281/zenodo.15206559 |
| Citations | 3,521 |
| Source | OpenAlex |