Search Results for author:
Found 3 papers, 3 papers with code
Scaling physics-informed hard constraints with mixture-of-experts
Our approach imposes the constraint over smaller decomposed domains, each of which is solved by an "expert" through differentiable optimization.
Neural Spectral Methods: Self-supervised learning in the spectral domain
In contrast to current machine learning approaches which enforce PDE constraints by minimizing the numerical quadrature of the residuals in the spatiotemporal domain, we leverage Parseval's identity and introduce a new training strategy through a \textit{spectral loss}.
TopoAct: Visually Exploring the Shape of Activations in Deep Learning
To understand how such performance is achieved, we probe a trained deep neural network by studying neuron activations, i. e., combinations of neuron firings, at various layers of the network in response to a particular input.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
