Related papers: Classification of Fermi-LAT unidentified gamma-ray…
B2013+370 and B2023+336 are two blazars at low-galactic latitude that were previously proposed to be the counterparts for the EGRET unidentified sources, 3EG J2016+3657 and 3EG J2027+3429. Gamma-ray emission associated with the EGRET…
We recently developed a procedure to recognize gamma-ray blazar candidates within the positional uncertainty regions of the unidentified/unassociated gamma-ray sources (UGSs). Such procedure was based on the discovery that Fermi blazars…
agtboost is an R package implementing fast gradient tree boosting computations in a manner similar to other established frameworks such as xgboost and LightGBM, but with significant decreases in computation time and required mathematical…
The capability of the Fermi Gamma-ray Burst Monitor (GBM) to localize gamma-ray bursts (GRBs) is evaluated for two different automated algorithms: the GBM Team's RoboBA algorithm and the independently developed BALROG algorithm. Through a…
Selecting radiology examination protocol is a repetitive, and time-consuming process. In this paper, we present a deep learning approach to automatically assign protocols to computer tomography examinations, by pre-training a…
As machine learning transitions increasingly towards real world applications controlling the test-time cost of algorithms becomes more and more crucial. Recent work, such as the Greedy Miser and Speedboost, incorporate test-time budget…
Understanding how "black-box" models arrive at their predictions has sparked significant interest from both within and outside the AI community. Our work focuses on doing this by generating local explanations about individual predictions…
We describe an image-based method that uses two radio criteria, compactness and spectral index, to identify promising pulsar candidates among Fermi Large Area Telescope (LAT) unassociated sources. These criteria are applied to those radio…
We discuss the time-series behavior of 8 extragalactic 3FGL sources away from the Galactic plane (i.e., $\mid b\mid \geq 10^{\circ}$) whose uncertainty ellipse contains a single X-ray and one radio source. The analysis was done using the…
We present a unified probabilistic gradient boosting framework for regression tasks that models and predicts the entire conditional distribution of a univariate response variable as a function of covariates. Our likelihood-based approach…
The Fermi GBM catalog provides a large database with many measured variables that can be used to explore and verify gamma-ray burst classification results. We have used Principal Component Analysis and statistical clustering techniques to…
Blazars are active galactic nuclei with relativistic jets pointed almost directly at Earth. Blazars are characterized by strong, apparently stochastic flux variability at virtually all observed wavelengths and timescales, from minutes to…
Despite the large number of discoveries made recently by Fermi, the origins of the so called unidentified gamma-ray sources remain unknown. The large number of these sources suggests that among them there could be a population that…
We report on the analysis of 13 gamma-ray pulsars discovered in the Einstein@Home blind search survey using Fermi Large Area Telescope (LAT) Pass 8 data. The 13 new gamma-ray pulsars were discovered by searching 118 unassociated LAT sources…
To maximize the discovery potential of future synoptic surveys, especially in the field of transient science, it will be necessary to use automatic classification to identify some of the astronomical sources. The data mining technique of…
Wide-field, multi-band surveys now detect millions of unresolved sources in nearby galaxy clusters, yet separating globular clusters (GCs) from foreground stars and background galaxies remains challenging. Scalable, automated classification…
Unsupervised Domain Adaptation for Regression (UDAR) aims to adapt models from a labeled source domain to an unlabeled target domain for regression tasks. Traditional feature alignment methods, successful in classification, often prove…
We perform a blind search for the variability of the gamma-ray sky in the energy range E>1 GeV using 308 weeks of the Fermi-LAT data. We use the technique based on the comparison of the weekly photon counts and exposures in sky pixels by…
We investigate star-galaxy classification for astronomical surveys in the context of four methods enabling the interpretation of black-box machine learning systems. The first is outputting and exploring the decision boundaries as given by…
The Fermi Large Area Telescope (LAT) Collaboration has recently released a catalog of 360 sources detected above 50 GeV (2FHL). This catalog was obtained using 80 months of data re-processed with Pass 8, the newest event-level analysis,…