Related papers: A Convolutional Neural Network based Cascade Recon…
The IceCube Neutrino Observatory instruments roughly one cubic kilometer of deep, glacial ice below the geographic South Pole with 5160 optical sensors to register the Cherenkov light of passing relativistic, charged particles. Since its…
Atmospheric neutrino oscillations with DeepCore; Supernova detection with IceCube and beyond; Study of South Pole ice transparency with IceCube flashers; Submitted papers to the 32nd International Cosmic Ray Conference, Beijing 2011.
Deep convolutional neural networks (CNNs) have recently achieved great success for single image super-resolution (SISR) task due to their powerful feature representation capabilities. The most recent deep learning based SISR methods focus…
Large neutrino detectors like IceCube monitor for core-collapse supernovae using low energy (MeV) neutrinos, with a reach to a supernova neutrino burst to the Magellanic Cloud. However, some models predict the emission of high energy…
IceCube-DeepCore is a compact Cherenkov detector located in the clear ice of the bottom center of the IceCube Neutrino Telescope. Its purpose is to enhance the sensitivity of IceCube for low neutrino energies (< 1 TeV) and to lower the…
We propose a novel deep learning tool in order to study the evolution of dark energy models. The aim is to combine two architectures: the Recurrent Neural Networks (RNN) and the Bayesian Neural Networks (BNN), we named this full network as…
IceCube is the first representative of the km^3 class of neutrino telescopes and currently the most sensitive detector to high-energy neutrinos. Its main mission is to search for Galactic and extragalactic sources of high-energy neutrinos,…
The precision anticipated from next-generation cosmic microwave background (CMB) surveys will create opportunities for characteristically new insights into cosmology. Secondary anisotropies of the CMB will have an increased importance in…
Deep-neural-network-based image reconstruction has demonstrated promising performance in medical imaging for under-sampled and low-dose scenarios. However, it requires large amount of memory and extensive time for the training. It is…
Artificial neural networks have recently shown great results in many disciplines and a variety of applications, including natural language understanding, speech processing, games and image data generation. One particular application in…
Neuron reconstruction is essential to generate exquisite neuron connectivity map for understanding brain function. Despite the significant amount of effect that has been made on automatic reconstruction methods, manual tracing by…
Image reconstruction for positron emission tomography (PET) is challenging because of the ill-conditioned tomographic problem and low counting statistics. Kernel methods address this challenge by using kernel representation to incorporate…
In this paper, we propose deformable deep convolutional neural networks for generic object detection. This new deep learning object detection framework has innovations in multiple aspects. In the proposed new deep architecture, a new…
The IceCube Neutrino Observatory, completed in December 2010 and located at the geographic South Pole, is the largest neutrino telescope in the world. IceCube includes the more densely instrumented DeepCore subarray, which increases…
IceCube is a km^3 scale neutrino detector being constructed deep in the Antarctic ice. When complete, IceCube will consist of 4800 optical modules deployed on 80 strings between 1450 and 2450 m of depth. During the 2007-2008 data taking…
The next galactic supernova presents a once-in-a-lifetime opportunity to obtain detailed information about the explosion of a star and the extreme conditions found within its core. A core-collapse supernova will produce a neutrino burst…
Convolutional neural networks (CNNs) have shown great capability of solving various artificial intelligence tasks. However, the increasing model size has raised challenges in employing them in resource-limited applications. In this work, we…
Supernovae Ia (SNe) can provide a unique window on the large scale structure (LSS) of the Universe at redshifts where few other observations are available, by solving the inversion problem (IP) consisting in reconstructing the LSS from its…
Deep learning architectures such as convolutional neural networks are the standard in computer vision for image processing tasks. Their accuracy however often comes at the cost of long and computationally expensive training, the need for…
Visual exploration of large multidimensional datasets has seen tremendous progress in recent years, allowing users to express rich data queries that produce informative visual summaries, all in real time. Techniques based on data cubes are…