Related papers: The Distributed and Unified Numerics Environment (…
Network embedding leverages the node proximity manifested to learn a low-dimensional node vector representation for each node in the network. The learned embeddings could advance various learning tasks such as node classification, network…
To improve predictive models for STEM applications, supplemental physics-based features computed from input parameters are introduced into single and multiple layers of a deep neural network (DNN). While many studies focus on informing DNNs…
High fidelity representation of shapes with arbitrary topology is an important problem for a variety of vision and graphics applications. Owing to their limited resolution, classical discrete shape representations using point clouds, voxels…
Deep Neural Networks (DNNs) are powerful tools that have shown extraordinary results in many scenarios, ranging from pattern recognition to complex robotic problems. However, their intricate designs and lack of transparency raise safety…
The proposed Deep Underground Neutrino Experiment (DUNE) utilizes a wide-band on-axis tunable muon-(anti)neutrino beam with a baseline of 1300 km to search for CP violation with high precision. Given the long baseline, DUNE is also…
The preponderance of matter over antimatter in the early universe, the dynamics of the supernovae that produced the heavy elements necessary for life, and whether protons eventually decay -- these mysteries at the forefront of particle…
Embedded distributed inference of Neural Networks has emerged as a promising approach for deploying machine-learning models on resource-constrained devices in an efficient and scalable manner. The inference task is distributed across a…
Mobile devices run deep learning models for various purposes, such as image classification and speech recognition. Due to the resource constraints of mobile devices, researchers have focused on either making a lightweight deep neural…
Recently, there has been an explosive growth of mobile and embedded applications using convolutional neural networks(CNNs). To alleviate their excessive computational demands, developers have traditionally resorted to cloud offloading,…
The Deep Underground Neutrino Experiment (DUNE) is a proposed long-baseline neutrino oscillation experiment that will project an on-axis wide-band neutrino beam over a distance of 1300 km to determine the unknowns in the neutrino sector.…
3D semantic scene completion and 2D semantic segmentation are two tightly correlated tasks that are both essential for indoor scene understanding, because they predict the same semantic classes, using positively correlated high-level…
The Domain Mixed Unit (DMU) is a new neural arithmetic unit that learns a single parameter gate that mixes between log-space and linear-space representations while performing either addition (DMU add) or subtraction (DMU sub). Two…
Although physics-informed neural networks (PINNs) have shown great potential in dealing with nonlinear partial differential equations (PDEs), it is common that PINNs will suffer from the problem of insufficient precision or obtaining…
Inverse problems involving differential equations often require identifying unknown parameters or functions from data. Existing approaches, such as Physics-Informed Neural Networks (PINNs), Universal Differential Equations (UDEs) and…
The Deep Underground Neutrino Experiment (DUNE) primarily aims to measure the yet unknown parameters of the standard three neutrino framework, i.e., the determination of Dirac CP phase ($\delta_{13}$), neutrino mass hierarchy (MH) and…
High-accuracy Dichotomous Image Segmentation (DIS) aims to pinpoint category-agnostic foreground objects from natural scenes. The main challenge for DIS involves identifying the highly accurate dominant area while rendering detailed object…
Dimensionality reduction methods such as t-SNE are designed to preserve local neighborhood structure but do not explicitly account for how probability mass is distributed, often leading to distortions of data density. We reformulate…
Deep learning models frequently encounter feature uncertainty in diverse learning scenarios, significantly impacting their performance and reliability. This challenge is particularly complex in multi-modal scenarios, where models must…
Many data-based statistical algorithms require that one find \textit{near or nearest neighbors} to a given vector among a set of points in that vector space, usually with Euclidean topology. The k-d data structure and search algorithms are…
In this talk we will review the major additions and improvements made to the ROOT system in the last 18 months and present our plans for future developments. The additons and improvements range from modifications to the I/O sub-system to…