Human-Readable Neuro-Fuzzy Networks from Frequent yet Discernible Patterns in Reward-Based Environments

Abstract

We propose self-organizing and simplifying neuro-fuzzy networks (NFNs) to yield transparent human-readable policies by exploiting fuzzy information granulation and graph theory. Deriving from social network analysis, we retain only the frequent-yet-discernible (FYD) patterns in NFNs and apply them to reward-based scenarios. The effectiveness of NFNs from FYD patterns is shown in classic control and a real-world classroom using an intelligent tutoring system to teach students.

Cite

Text

Hostetter et al. "Human-Readable Neuro-Fuzzy Networks from Frequent yet Discernible Patterns in Reward-Based Environments." International Joint Conference on Artificial Intelligence, 2025. doi:10.24963/IJCAI.2025/505

Markdown

[Hostetter et al. "Human-Readable Neuro-Fuzzy Networks from Frequent yet Discernible Patterns in Reward-Based Environments." International Joint Conference on Artificial Intelligence, 2025.](https://mlanthology.org/ijcai/2025/hostetter2025ijcai-human/) doi:10.24963/IJCAI.2025/505

BibTeX

@inproceedings{hostetter2025ijcai-human,
  title     = {{Human-Readable Neuro-Fuzzy Networks from Frequent yet Discernible Patterns in Reward-Based Environments}},
  author    = {Hostetter, John Wesley and Saha, Adittya Soukarjya and Islam, Md. Mirajul and Barnes, Tiffany and Chi, Min},
  booktitle = {International Joint Conference on Artificial Intelligence},
  year      = {2025},
  pages     = {4535-4543},
  doi       = {10.24963/IJCAI.2025/505},
  url       = {https://mlanthology.org/ijcai/2025/hostetter2025ijcai-human/}
}