Strongly interacting dark sectors predict novel LHC signatures such as semi-visible jets resulting from dark showers that contain both stable and unstable dark mesons. Distinguishing such semi-visible jets from large QCD backgrounds is difficult and constitutes an exciting challenge for jet classification. In this article we explore the potential of supervised deep neural networks to identify semi-visible jets. We show that dynamic graph convolutional neural networks operating on so-called particle clouds outperform convolutional neural networks analysing jet images as well as other neural networks based on Lorentz vectors. We investigate how the performance depends on the properties of the dark shower and discuss training on mixed samples as a strategy to reduce model dependence. By modifying an existing mono-jet analysis we show that LHC sensitivity to dark sectors can be enhanced by more than an order of magnitude by using the dynamic graph network as a dark shower tagger.

Autoencoders are widely used in machine learning applications, in particular for anomaly detection. Hence, they have been introduced in high energy physics as a promising tool for model-independent new physics searches. We scrutinize the usage of autoencoders for unsupervised anomaly detection based on reconstruction loss to show their capabilities, but also their limitations. As a particle physics benchmark scenario, we study the tagging of top jet images in a background of QCD jet images. Although we reproduce the positive results from the literature, we show that the standard autoencoder setup cannot be considered as a model-independent anomaly tagger by inverting the task: due to the sparsity and the specific structure of the jet images, the autoencoder fails to tag QCD jets if it is trained on top jets even in a semi-supervised setup. Since the same autoencoder architecture can be a good tagger for a specific example of an anomaly and a bad tagger for a different example, we suggest improved performance measures for the task of model-independent anomaly detection. We also improve the capability of the autoencoder to learn non-trivial features of the jet images, such that it is able to achieve both top jet tagging and the inverse task of QCD jet tagging with the same setup. However, we want to stress that a truly model-independent and powerful autoencoder-based unsupervised jet tagger still needs to be developed.

Searches for anomalies are the main motivation for the LHC and define key analysis steps, including triggers. We discuss how LHC anomalies can be defined through probability density estimates, evaluated in a physics space or in an appropriate neural network latent space. We illustrate this for classical k-means clustering, a Dirichlet variational autoencoder, and invertible neural networks. For two especially challenging scenarios of jets from a dark sector we evaluate the strengths and limitations of each method.

Despite the growing number of gamma-ray sources detected by the Fermi-Large Area Telescope (LAT), about one third of the sources in each survey remains of uncertain type. We present a new deep neural network approach for the classification of unidentified or unassociated gamma-ray sources in the last release of the Fermi-LAT catalogue (4FGL-DR2) obtained with 10 years of data. In contrast to previous work, our method directly uses the measurements of the photon energy spectrum and time series as input for the classification, instead of specific, human-crafted features. Dense neural networks, and for the first time in the context of gamma-ray source classification recurrent neural networks, are studied in depth. We focus on the separation between extragalactic sources, i.e. Active Galactic Nuclei, and Galactic pulsars, and on the further classification of pulsars into young and millisecond pulsars. Our neural network architectures provide powerful classifiers, with a performance that is comparable to previous analyses based on human-crafted features. Our benchmark neural network predicts that of the sources of uncertain type in the 4FGL-DR2 catalogue, 1050 are Active Galactic Nuclei and 78 are Galactic pulsars, with both classes following the expected sky distribution and the clustering in the variability-curvature plane. We investigate the problem of sample selection bias by testing our architectures against a cross-match test data set using an older catalogue, and propose a feature selection algorithm using autoencoders. Our list of high-confidence candidate sources labelled by the neural networks provides a set of targets for further multiwavelength observations addressed to identify their nature. The deep neural network architectures we develop can be easily extended to include specific features, as well as multiwavelength data on the source photon energy and time spectra coming from different instruments.

The use of Bayesian neural networks is a novel approach for the classification of γ-ray sources. We focus on the classification of Fermi-LAT blazar candidates, which can be divided into BL Lacertae objects and Flat Spectrum Radio Quasars. In contrast to conventional dense networks, Bayesian neural networks provide a reliable estimate of the uncertainty of the network predictions. We explore the correspondence between conventional and Bayesian neural networks and the effect of data augmentation. We find that Bayesian neural networks provide a robust classifier with reliable uncertainty estimates and are particularly well suited for classification problems that are based on comparatively small and imbalanced data sets. The results of our blazar candidate classification are valuable input for population studies aimed at constraining the blazar luminosity function and to guide future observational campaigns.