Related papers: 2D Convolutional Neural Network for Event Reconstr…
Deep learning has been utilized for the statistical downscaling of climate data. Specifically, a two-dimensional (2D) convolutional neural network (CNN) has been successfully applied to precipitation estimation. This study implements a…
The IceCube Neutrino Observatory at the South Pole detects neutrinos of astrophysical origin via their interactions with ice. The main array is optimized for the detection of neutrinos with energies above 1 TeV. A much smaller infill array,…
The IceCube Neutrino Observatory is the world's largest high energy neutrino telescope, using the Antarctic ice cap as a Cherenkov detector medium. DeepCore, the low energy extension to IceCube, is an infill array with a fiducial volume of…
We show that study of the atmospheric neutrinos in the 10--100 GeV energy range by DeepCore sub-array of the IceCube Neutrino Observatory can substantially constrain the mixing of sterile neutrinos of mass $\sim 1$ eV with active neutrinos.…
In the present work, 3D convolutional neural networks (CNNs) are trained to link random heterogeneous, two-phase materials of arbitrary phase fractions to their elastic macroscale stiffness thus replacing explicit homogenization…
Deep learning has established many new state of the art solutions in the last decade in areas such as object, scene and speech recognition. In particular Convolutional Neural Network (CNN) is a category of deep learning which obtains…
The Jiangmen Underground Neutrino Observatory (JUNO) is an experiment designed to study neutrino oscillations. Determination of neutrino mass ordering and precise measurement of neutrino oscillation parameters $\sin^2 2\theta_{12}$, $\Delta…
In the effort to obtain a precise measurement of leptonic CP-violation with the ESS$\nu$SB experiment, accurate and fast reconstruction of detector events plays a pivotal role. In this work, we examine the possibility of replacing the…
The IceCube Neutrino Observatory is highly sensitive to neutrino bursts of $\mathcal{O}$(10) MeV energy that are would be generated by core collapse supernovae in our Galaxy. It will resolve temporal structures in supernova light curves…
Deep Neural Networks (DNNs) have shown unparalleled achievements in numerous applications, reflecting their proficiency in managing vast data sets. Yet, their static structure limits their adaptability in ever-changing environments. This…
We describe the class of convexified convolutional neural networks (CCNNs), which capture the parameter sharing of convolutional neural networks in a convex manner. By representing the nonlinear convolutional filters as vectors in a…
It remains a challenge to efficiently extract spatialtemporal information from skeleton sequences for 3D human action recognition. Although most recent action recognition methods are based on Recurrent Neural Networks which present…
In recent years, convolutional neural networks (CNN) have played an important role in the field of deep learning. Variants of CNN's have proven to be very successful in classification tasks across different domains. However, there are two…
Deep convolutional neural networks (ConvNets) of 3-dimensional kernels allow joint modeling of spatiotemporal features. These networks have improved performance of video and volumetric image analysis, but have been limited in size due to…
Neutrinos produced in core-collapse supernova offer a direct probe into the hydrodynamics and energy transport mechanisms during the collapse and play a pivotal role in the shock revival and success of the supernova explosion. Fast-time…
The IceCube-Gen2 Neutrino Observatory is proposed to extend the all-flavour energy range of IceCube beyond PeV energies. It will comprise two key components: I) An enlarged 8$\,$km$^3$ in-ice optical Cherenkov array to measure the…
The IceCube Neutrino Observatory relies on an array of photomultiplier tubes to detect Cherenkov light produced by charged particles in the South Pole ice. IceCube data analyses depend on an in-depth characterization of the glacial ice, and…
In-ice radio-detection is a promising technique to discover and characterize ultra-high-energy (UHE) neutrinos, with energies above 100 PeV, adopted by present - ARA, ARIANNA, and RNO-G - and planned - IceCube-Gen2. So far, their ability to…
The IceCube project has transformed one cubic kilometer of deep natural Antarctic ice into a Cherenkov detector. Muon neutrinos are detected and their direction inferred by mapping the light produced by the secondary muon track inside the…
We have developed a convolutional neural network (CNN) that can make a pixel-level prediction of objects in image data recorded by a liquid argon time projection chamber (LArTPC) for the first time. We describe the network design, training…