Neural ordinary differential equations (neural ODEs) are a popular family of continuous-
depth deep learning models. In this work, we consider a large family of parameterized ODEs …

Residual neural networks are state-of-the-art deep learning models. Their continuous-depth
analog, neural ordinary differential equations (ODEs), are also widely used. Despite their …

A bstract We employ a deep learning method to deduce the bulk spacetime from boundary
optical conductivity. We apply the neural ordinary differential equation technique, tailored for …

The ResNet architecture has been widely adopted in deep learning due to its significant
boost to performance through the use of simple skip connections, yet the underlying …

Deep Feedforward Neural Networks (FNNs) with skip connections have revolutionized
various image recognition tasks. In this paper, we propose a novel architecture called …

We sample from a given target distribution by constructing a neural network which maps
samples from a simple reference, eg the standard normal distribution, to samples from the …

Deep learning has made significant applications in the field of data science and natural
science. Some studies have linked deep neural networks to dynamic systems, but the …

This paper introduces a new Convolutional Neural Network (ConvNet) architecture inspired
by a class of partial differential equations (PDEs) called quasi-linear hyperbolic systems …

The largest eigenvalue of the Hessian, or sharpness, of neural networks is a key quantity to
understand their optimization dynamics. In this paper, we study the sharpness of deep linear …

The increasing availability of global observational data has sparked a demand for deep
learning algorithms on spherical grids to enable intelligent analysis at a global scale …