相关论文: Classification of Fermi-LAT blazars with Bayesian …

Context. Blazars are a distinct subclass of active galactic nuclei (AGN), known for their fast variability, high polarization, and intense emission across the electromagnetic spectrum, from radio waves to gamma rays. Gamma-ray blazar…

Bayesian Neural Networks (BNNs) offer probability distributions for model parameters, enabling uncertainty quantification in predictions. However, they often underperform compared to deterministic neural networks. Utilizing mutual learning…

Convolution Neural Networks trained for the task of lens finding with similar architecture and training data as is commonly found in the literature are biased classifiers. An understanding of the selection function of lens finding neural…

Blazars are the most common sources of $\gamma$-ray photons in the extragalactic sky. Their $\gamma$-ray light curves are characterized by bright flaring episodes, similarly to what is observed at longer wavelengths. These gamma-ray bursts…

The classification of gamma-ray-detected blazar candidates of uncertain type (BCU) is a relevant problem in extragalactic gamma-ray astronomy. Here we report the optical spectroscopic characterization, using two 3-4~m class telescopes,…

Recently, combinations of generative and Bayesian machine learning have been introduced in particle physics for both fast detector simulation and inference tasks. These neural networks aim to quantify the uncertainty on the generated…

Bayesian inference is used extensively to quantify the uncertainty in an inferred field given the measurement of a related field when the two are linked by a mathematical model. Despite its many applications, Bayesian inference faces…

The global contribution of unresolved gamma-ray point sources to the extragalactic gamma-ray background has been recently measured down to gamma-ray fluxes lower than those reached with standard source detection techniques, and by employing…

One of the goals of current particle physics research is to obtain evidence for new physics, that is, physics beyond the Standard Model (BSM), at accelerators such as the Large Hadron Collider (LHC) at CERN. The searches for new physics are…

We present a new method to approximate posterior probabilities of Bayesian Network using Deep Neural Network. Experiment results on several public Bayesian Network datasets shows that Deep Neural Network is capable of learning joint…

Neural Linear Models (NLM) are deep Bayesian models that produce predictive uncertainty by learning features from the data and then performing Bayesian linear regression over these features. Despite their popularity, few works have focused…

We present a novel approach for training deep neural networks in a Bayesian way. Classical, i.e. non-Bayesian, deep learning has two major drawbacks both originating from the fact that network parameters are considered to be deterministic.…

To advance the transparency of learning machines such as Deep Neural Networks (DNNs), the field of Explainable AI (XAI) was established to provide interpretations of DNNs' predictions. While different explanation techniques exist, a popular…

Neural Networks (NNs) have been widely {used in supervised learning} due to their ability to model complex nonlinear patterns, often presented in high-dimensional data such as images and text. However, traditional NNs often lack the ability…

Bayesian Neural Networks (BNNs) offer a principled and natural framework for proper uncertainty quantification in the context of deep learning. They address the typical challenges associated with conventional deep learning methods, such as…

Recurrent neural networks (RNNs) are nonlinear dynamical models commonly used in the machine learning and dynamical systems literature to represent complex dynamical or sequential relationships between variables. More recently, as deep…

We present statistical analyses of a large homogenous data sample of Fermi-detected blazars thoroughly studied in order to reassess the relationship between flat-spectrum radio quasars (FSRQs) and subclasses of BL Lacertae objects (BL Lacs)…

In the third catalog of active galactic nuclei detected by the $Fermi$ Large Area Telescope Clean (3LAC) sample, there are 402 blazars candidates of uncertain type (BCU). The proposed analysis will help to evaluate the potential optical…

Unassociated Fermi-LAT sources provide a population with discovery potential. We discuss efforts to find new source associations for this population, and summarize the successes to date. We discuss how the measured gamma-ray properties of…

Bayesian networks in their Factor Graph Reduced Normal Form (FGrn) are a powerful paradigm for implementing inference graphs. Unfortunately, the computational and memory costs of these networks may be considerable, even for relatively small…