Connections between Numerical Algorithms for PDEs and Neural Networks

by   Tobias Alt, et al.

We investigate numerous structural connections between numerical algorithms for partial differential equations (PDEs) and neural architectures. Our goal is to transfer the rich set of mathematical foundations from the world of PDEs to neural networks. Besides structural insights we provide concrete examples and experimental evaluations of the resulting architectures. Using the example of generalised nonlinear diffusion in 1D, we consider explicit schemes, acceleration strategies thereof, implicit schemes, and multigrid approaches. We connect these concepts to residual networks, recurrent neural networks, and U-net architectures. Our findings inspire a symmetric residual network design with provable stability guarantees and justify the effectiveness of skip connections in neural networks from a numerical perspective. Moreover, we present U-net architectures that implement multigrid techniques for learning efficient solutions of partial differential equation models, and motivate uncommon design choices such as trainable nonmonotone activation functions. Experimental evaluations show that the proposed architectures save half of the trainable parameters and can thus outperform standard ones with the same model complexity. Our considerations serve as a basis for explaining the success of popular neural architectures and provide a blueprint for developing new mathematically well-founded neural building blocks.


Translating Numerical Concepts for PDEs into Neural Architectures

We investigate what can be learned from translating numerical algorithms...

Designing Rotationally Invariant Neural Networks from PDEs and Variational Methods

Partial differential equation (PDE) models and their associated variatio...

Partial Differential Equations is All You Need for Generating Neural Architectures – A Theory for Physical Artificial Intelligence Systems

In this work, we generalize the reaction-diffusion equation in statistic...

Approximation properties of Residual Neural Networks for Kolmogorov PDEs

In recent years residual neural networks (ResNets) as introduced by [He,...

IMEXnet: A Forward Stable Deep Neural Network

Deep convolutional neural networks have revolutionized many machine lear...

Please sign up or login with your details

Forgot password? Click here to reset