Search Results for author:
Found 10 papers, 3 papers with code
Feature-Action Design Patterns for Storytelling Visualizations with Time Series Data
Motivated initially by the need to communicate time series data during the COVID-19 pandemic, we developed a novel computer-assisted method for meta-authoring of stories, which enables the design of storyboards that include feature-action patterns in anticipation of potential features that may appear in dynamically arrived or selected data.
MLCommons Cloud Masking Benchmark with Early Stopping
We provide a description of the cloud masking benchmark, as well as a summary of our submission to MLCommons on the benchmark experiment we conducted.
Zero Coordinate Shift: Whetted Automatic Differentiation for Physics-informed Operator Learning
Automatic differentiation (AD) is a critical step in physics-informed machine learning, required for computing the high-order derivatives of network output w. r. t.
Padding-free Convolution based on Preservation of Differential Characteristics of Kernels
Convolution is a fundamental operation in image processing and machine learning.
On the Compatibility between Neural Networks and Partial Differential Equations for Physics-informed Learning
Inspired by this pitfall, we prove that a linear PDE up to the $n$-th order can be strictly satisfied by an MLP with $C^n$ activation functions when the weights of its output layer lie on a certain hyperplane, as called the out-layer-hyperplane.
Affinity-VAE for disentanglement, clustering and classification of objects in multidimensional image data
In this work we present affinity-VAE: a framework for automatic clustering and classification of objects in multidimensional image data based on their similarity.
Discovering the building blocks of dark matter halo density profiles with neural networks
The additional dimension in the representation contains information about the infalling material in the outer profiles of dark matter halos, thus discovering the splashback boundary of halos without prior knowledge of the halos' dynamical history.
Disentangling Autoencoders (DAE)
Noting the importance of factorizing (or disentangling) the latent space, we propose a novel, non-probabilistic disentangling framework for autoencoders, based on the principles of symmetry transformations in group-theory.
Scientific Machine Learning Benchmarks
In this paper, we describe our approach to the development of scientific machine learning benchmarks and review other approaches to benchmarking scientific machine learning.
Deep learning insights into cosmological structure formation
We train a three-dimensional convolutional neural network (CNN) to predict the mass of dark matter halos from the initial conditions, and quantify in full generality the amounts of information in the isotropic and anisotropic aspects of the initial density field about final halo masses.
