Related papers: Deep Learning as a Parton Shower

How do neural networks trained over sequences acquire the ability to perform structured operations, such as arithmetic, geometric, and algorithmic computation? To gain insight into this question, we introduce the sequential group…

Parton showers lie at the core of Shower Monte Carlo event generators, the default theoretical tools used to interpret collider data. In these proceedings, we summarise the strategy of the PanScales collaboration that led to the attainment…

Deep learning became the method of choice in recent year for solving a wide variety of predictive analytics tasks. For sequence prediction, recurrent neural networks (RNN) are often the go-to architecture for exploiting sequential…

Effective training of Deep Neural Networks requires massive amounts of data and compute. As a result, longer times are needed to train complex models requiring large datasets, which can severely limit research on model development and the…

This paper explores a deep learning based robot intelligent model that renders robots learn and reason for complex tasks. First, by constructing a network of environmental factor matrix to stimulate the learning process of the robot…

Current fine-grained classification approaches often rely on a robust localization of object parts to extract localized feature representations suitable for discrimination. However, part localization is a challenging task due to the large…

We present a novel deep neural network architecture for representing robot experiences in an episodic-like memory which facilitates encoding, recalling, and predicting action experiences. Our proposed unsupervised deep episodic memory model…

The goal of this work is to investigate the possibility of improving current gamma/hadron discrimination based on their shower patterns recorded on the ground. To this end we propose the use of Convolutional Neural Networks (CNNs) for their…

This work proposes an autoencoder neural network as a non-linear generalization of projection-based methods for solving Partial Differential Equations (PDEs). The proposed deep learning architecture presented is capable of generating the…

We present a Monte Carlo simulation of the perturbative Quantum Chromodynamics (pQCD) shower developing after a hard process embedded in a heavy-ion collision. The main assumption is that the cascade of branching partons traverses a medium…

Machine Learning is a powerful tool to reveal and exploit correlations in a multi-dimensional parameter space. Making predictions from such correlations is a highly non-trivial task, in particular when the details of the underlying dynamics…

It is useful to describe a leading order parton shower as the solution of a linear equation that specifies how the state of the partons evolves. This description involves an essential approximation of a strong ordering of virtualities as…

The choice of optimal event variables is crucial for achieving the maximal sensitivity of experimental analyses. Over time, physicists have derived suitable kinematic variables for many typical event topologies in collider physics. Here we…

This paper takes a parallel learning approach for robust and transparent AI. A deep neural network is trained in parallel on multiple tasks, where each task is trained only on a subset of the network resources. Each subset consists of…

Unsupervised learning of visual similarities is of paramount importance to computer vision, particularly due to lacking training data for fine-grained similarities. Deep learning of similarities is often based on relationships between pairs…

We propose a Deep Texture Encoding Network (Deep-TEN) with a novel Encoding Layer integrated on top of convolutional layers, which ports the entire dictionary learning and encoding pipeline into a single model. Current methods build from…

We describe an algorithm for improving subsequent parton shower emissions by full SU(3) color correlations in the framework of a dipole-type shower. As a proof of concept, we present results from the first implementation of such an…

Deep learning can be used to extract meaningful results from images. In this paper, we used convolutional neural networks combined with recurrent neural networks on images of plasmonic structures and extract absorption data form them. To…

In the context of classification problems, Deep Learning (DL) approaches represent state of art. Many DL approaches are based on variations of standard multi-layer feed-forward neural networks. These are also referred to as deep networks.…

Programs that calculate observables in quantum chromodynamics at next-to-leading order typically generate events that consist of partons rather than hadrons -- and just a few partons at that. These programs would be much more useful if the…