Functional-Hybrid Modeling through automated adaptive symbolic regression for interpretable mathematical expressions
H. Narayanan, M. N. C. Bournazou, G. Guillen-Gosalbez, A. Butte
This paper introduces a hybrid modeling framework that combines domain-specific functional beliefs with symbolic regression to create interpretable mathematical models, showing improved performance over traditional neural networks in biochemical systems.
bioRxiv · Jun 9, 2021Bioengineering