Analytics and Information Systems

Introduction to Analytics

PhD, Computer Science, North Carolina State University, 2025

MS, Computer Science, North Carolina State University, 2022

BS, Computer Science, The Pennsylvania State University, 2019

Dr. John Wesley Hostetter is an Assistant Professor in the Department of Analytics and Information Systems. His research involves neuro-symbolic architectures that are intrinsically transparent —along with other benefits — with the ultimate goal of leveraging them for explainable artificial intelligence. These novel sample-efficient, transparent neural architectures are called neuro-fuzzy networks (NFNs); they are naturally robust to missing data and possess universal function approximation guarantees. Dr. Hostetter’s research advances the current state-of-the-art of these neuro-symbolic architectures. His prior research has been published in respected international conferences, such as AAMAS and IJCAI.

Hostetter, J. W., Saha, A. S., Islam, M. M., Barnes, T., & Chi, M. (2025). Human-readable neuro-fuzzy networks from frequent yet discernible patterns in reward-based environments. In Proceedings of the 34th International Joint Conference on Artificial Intelligence (IJCAI).

Hostetter, J. W. (2025). Gradient-based neuroplastic adaptation for concurrent optimization of neuro-fuzzy networks (Doctoral dissertation, North Carolina State University).

Abdelshiheed, M., Moulder, R., Hostetter, J. W., Barnes, T., & Chi, M. (2024). Example, nudge, or practice? Assessing metacognitive knowledge transfer of factual and procedural learners. User Modeling and User-Adapted Interaction., 34(5), 1745–1775.

Islam, M. M., Yang, X., Hostetter, J. W., Saha, A. S., & Chi, M. (2024). A generalized apprenticeship learning framework for modeling heterogeneous student pedagogical strategies. In Proceedings of the 17th International Conference on Educational Data Mining (EDM).

Hostetter, J. W., Abdelshiheed, M., Barnes, T., & Chi, M. (2023). A self-organizing neuro-fuzzy Q-network: Systematic design with offline hybrid learning. In Proceedings of the 22nd International Conference on Autonomous Agents and Multiagent Systems (AAMAS).