AINeutralarXiv – CS AI · 5h ago6/10
🧠
Modeling Nonlinear Feature Interactions with Product-Unit Residual Networks
Researchers introduce Product-Unit Residual Networks (PURe), a neural architecture that explicitly models nonlinear feature interactions through multiplicative units combined with residual connections. The approach demonstrates improved interpretability, robustness to noise, and sample efficiency compared to standard MLPs across synthetic and real-world datasets.