This work presents a methodology for training explainable neural-network models based on Generalized Additive Models (GAMs), combining the predictive power of deep learning with the interpretability of additive statistical models. The proposed framework independently trains neural networks to estimate feature contributions, providing transparent and accountable AI systems suitable for high-risk applications.
The presentation discusses theoretical foundations, optimization strategies, and practical applications of Generalized Additive Neural Networks in explainable artificial intelligence and trustworthy machine learning.