MixFunn: A Neural Network for Differential Equations with Improved Generalization and Interpretability

📅 2025-03-28
📈 Citations: 0
Influential: 0
📄 PDF
🤖 AI Summary
Existing differential equation solvers face limitations in accuracy, generalization, and interpretability. To address these challenges, this paper proposes MixFunn—a novel neural network architecture featuring hybrid functional neurons and second-order neurons, integrated within the physics-informed neural networks (PINNs) framework. This design markedly enhances representational capacity while reducing parameter count by four orders of magnitude. Crucially, MixFunn enables direct extraction of closed-form analytical approximations from the trained model. Evaluated across diverse partial differential equations from classical mechanics, quantum mechanics, and fluid dynamics, MixFunn achieves significantly higher solution accuracy and demonstrates strong out-of-distribution generalization. The core contribution lies in unifying high accuracy, lightweight modeling, and inherent interpretability—establishing a new paradigm for scientific machine learning that bridges theoretical rigor and engineering practicality.

Technology Category

Application Category

📝 Abstract
We introduce MixFunn, a novel neural network architecture designed to solve differential equations with enhanced precision, interpretability, and generalization capability. The architecture comprises two key components: the mixed-function neuron, which integrates multiple parameterized nonlinear functions to improve representational flexibility, and the second-order neuron, which combines a linear transformation of its inputs with a quadratic term to capture cross-combinations of input variables. These features significantly enhance the expressive power of the network, enabling it to achieve comparable or superior results with drastically fewer parameters and a reduction of up to four orders of magnitude compared to conventional approaches. We applied MixFunn in a physics-informed setting to solve differential equations in classical mechanics, quantum mechanics, and fluid dynamics, demonstrating its effectiveness in achieving higher accuracy and improved generalization to regions outside the training domain relative to standard machine learning models. Furthermore, the architecture facilitates the extraction of interpretable analytical expressions, offering valuable insights into the underlying solutions.
Problem

Research questions and friction points this paper is trying to address.

Solve differential equations with enhanced precision and interpretability
Improve generalization capability outside training domain
Extract interpretable analytical expressions from solutions
Innovation

Methods, ideas, or system contributions that make the work stand out.

Mixed-function neuron enhances representational flexibility
Second-order neuron captures cross-combinations of inputs
Fewer parameters with higher accuracy and interpretability
🔎 Similar Papers
No similar papers found.
T
Tiago de Souza Farias
Physics Department, Federal University of São Carlos, 13565-905, São Carlos, SP, Brazil
G
Gubio Gomes de Lima
Physics Department, Federal University of São Carlos, 13565-905, São Carlos, SP, Brazil
J
Jonas Maziero
Physics Department, Federal University of Santa Maria, 97105-900, Santa Maria, RS, Brazil
C
Celso J. Villas-Boas
Physics Department, Federal University of São Carlos, 13565-905, São Carlos, SP, Brazil