Explainable Generalized Additive Neural Networks with Independent Neural Network Training
Published in 16th International Conference of the ERCIM WG on Computational and Methodological Statistics (CFE-CMStatistics 2023), 2023
Recommended citation: Ortega-Fernández, I., & Sestelo, M. (2023). Explainable Generalized Additive Neural Networks with Independent Neural Network Training. Poster presentation at CFE-CMStatistics 2023. https://cmstatistics.org/
This work introduces a Generalized Additive Neural Network framework designed to improve explainability in deep-learning models through independent neural-network training for feature-effect estimation.
The proposed methodology combines concepts from statistical modeling and deep learning to develop interpretable neural architectures capable of maintaining predictive performance while improving transparency and accountability in AI systems.