Mechanistic Neural Networks for Scientific Machine Learning
This work addresses the need for more interpretable and efficient neural network models in scientific domains, offering a novel approach that integrates mechanistic principles, though it appears incremental in combining existing ideas with new solver techniques.
The paper tackles the problem of enhancing interpretability and efficiency in scientific machine learning by introducing Mechanistic Neural Networks, which incorporate a Mechanistic Block and a novel Relaxed Linear Programming Solver (NeuRLP) to learn governing differential equations, resulting in significant performance improvements against state-of-the-art methods.
This paper presents Mechanistic Neural Networks, a neural network design for machine learning applications in the sciences. It incorporates a new Mechanistic Block in standard architectures to explicitly learn governing differential equations as representations, revealing the underlying dynamics of data and enhancing interpretability and efficiency in data modeling. Central to our approach is a novel Relaxed Linear Programming Solver (NeuRLP) inspired by a technique that reduces solving linear ODEs to solving linear programs. This integrates well with neural networks and surpasses the limitations of traditional ODE solvers enabling scalable GPU parallel processing. Overall, Mechanistic Neural Networks demonstrate their versatility for scientific machine learning applications, adeptly managing tasks from equation discovery to dynamic systems modeling. We prove their comprehensive capabilities in analyzing and interpreting complex scientific data across various applications, showing significant performance against specialized state-of-the-art methods.