Related papers: Background rejection in NEXT using deep neural net…

The widespread adoption of deep learning is often attributed to its automatic feature construction with minimal inductive bias. However, in many real-world tasks, the learned function is intended to satisfy domain-specific constraints. We…

Event cameras provide a number of benefits over traditional cameras, such as the ability to track incredibly fast motions, high dynamic range, and low power consumption. However, their application into computer vision problems, many of…

Context plays an important role in visual pattern recognition as it provides complementary clues for different learning tasks including image classification and annotation. In the particular scenario of kernel learning, the general recipe…

The CYGNO experiment employs an optical-readout Time Projection Chamber (TPC) to search for rare low-energy interactions using finely resolved scintillation images. While the optical readout provides rich topological information, it…

Recent work has shown that deep neural networks are highly sensitive to tiny perturbations of input images, giving rise to adversarial examples. Though this property is usually considered a weakness of learned models, we explore whether it…

Training deep neural networks (DNNs) usually requires massive training data and computational resources. Users who cannot afford this may prefer to outsource training to a third party or resort to publicly available pre-trained models.…

Methods for source detection in high noise environments are important for single-photon emission computed tomography (SPECT) medical imaging and especially crucial for homeland security applications, which is our main interest. In the…

We present a learning-based approach for removing unwanted obstructions, such as window reflections, fence occlusions or raindrops, from a short sequence of images captured by a moving camera. Our method leverages the motion differences…

We show how event topology classification based on deep learning could be used to improve the purity of data samples selected in real time at at the Large Hadron Collider. We consider different data representations, on which different kinds…

Context matters! Nevertheless, there has not been much research in exploiting contextual information in deep neural networks. For most part, the entire usage of contextual information has been limited to recurrent neural networks. Attention…

While deep learning models often achieve strong task performance, their successes are hampered by their inability to disentangle spurious correlations from causative factors, such as when they use protected attributes (e.g., race, gender,…

In recent years, neural networks have continued to flourish, achieving high efficiency in detecting relevant objects in photos or simply recognizing (classifying) these objects - mainly using CNN networks. Current solutions, however, are…

We describe a strategy for constructing a neural network jet substructure tagger which powerfully discriminates boosted decay signals while remaining largely uncorrelated with the jet mass. This reduces the impact of systematic…

We develop a Deep-Text Recurrent Network (DTRN) that regards scene text reading as a sequence labelling problem. We leverage recent advances of deep convolutional neural networks to generate an ordered high-level sequence from a whole word…

Resistive Plate Chambers (RPCs) are widely used as tracking detectors in many high-energy physics experiments. It has been observed that low-resistive bakelite RPC prototypes frequently exhibit a secondary hit component, appearing as a long…

We describe an alternative learning method for neural networks, which we call Blind Descent. By design, Blind Descent does not face problems like exploding or vanishing gradients. In Blind Descent, gradients are not used to guide the…

Neutrinoless double beta decay is a hypothetical, very slow nuclear transition in which two neutrons undergo beta decay simultaneously and without the emission of neutrinos. The importance of this process goes beyond its intrinsic interest:…

The Neutrino Experiment with a Xenon TPC (NEXT) is intended to investigate the neutrinoless double beta decay of 136Xe, which requires a severe suppression of potential backgrounds. An extensive screening and material selection process is…

Understanding how deep neural networks learn remains a fundamental challenge in modern machine learning. A growing body of evidence suggests that training dynamics undergo a distinct phase transition, yet our understanding of this…

We present two analysis techniques for distinguishing background events induced by neutrons from photon signal events in the search for the rare $K^0_L\rightarrow\pi^0\nu\bar{\nu}$ decay at the J-PARC KOTO experiment. These techniques…