Government
SEVIR: A Storm Event Imagery Dataset for Deep Learning Applications in Radar and Satellite Meteorology Mark S. Veillette
Modern deep learning approaches have shown promising results in meteorological applications like precipitation nowcasting, synthetic radar generation, front detection and several others. In order to effectively train and validate these complex algorithms, large and diverse datasets containing high-resolution imagery are required.
Multiwavelet-based Operator Learning for Differential Equations
The projected kernel is trained at multiple scales derived from using repeated computation of multiwavelet transform. This allows learning the complex dependencies at various scales and results in a resolution-independent scheme.
Well-tuned Simple Nets Excel on Tabular Datasets
Tabular datasets are the last "unconquered castle" for deep learning, with traditional
Particle Cloud Generation with Message Passing Generative Adversarial Networks
However, despite jets having a natural representation as a set of particles in momentum-space, a.k.a. a particle cloud, there exist no generative
Strongly Incremental Constituency Parsing with Graph Neural Networks
Parsing sentences into syntax trees can benefit downstream applications in NLP . Transition-based parsers build trees by executing actions in a state transition system.
The Convex Relaxation Barrier, Revisited: Tightened Single-Neuron Relaxations for Neural Network Verification
A fundamental problem in deep neural networks is to verify or certify that a trained network is robust, i.e. not susceptible to adversarial attacks [