Related papers: Back to the Formula -- LHC Edition

This study reports an unintuitive finding that positional encoding enhances learning of recurrent neural networks (RNNs). Positional encoding is a high-dimensional representation of time indices on input data. Most famously, positional…

We present a new approach to 3D object representation where a neural network encodes the geometry of an object directly into the weights and biases of a second 'mapping' network. This mapping network can be used to reconstruct an object by…

Finite-volume extrapolation is an important step for extracting physical observables from lattice calculations. However, it is a significant challenge for the system with long-range interactions. We employ symbolic regression to regress…

The W-fusion scattering process W+W- --> ZZ for off-shell W bosons is studied, focusing on the issue of its high-energy behaviour which is known to be anomalous. It is shown that the unitarity violating terms can be isolated and extracted…

Symbolic regression searches for analytic expressions that accurately describe studied phenomena. The main attraction of this approach is that it returns an interpretable model that can be insightful to users. Historically, the majority of…

Machine learning has played an important role in the analysis of high-energy physics data for decades. The emergence of deep learning in 2012 allowed for machine learning tools which could adeptly handle higher-dimensional and more complex…

Vector Boson Fusion (VBF) is a promising discovery level process in the Higgs search at the LHC. Nevertheless, that search depends on understanding the detector response to a good level of accuracy. Therefore, it is useful to have a known…

The ability of deep learning (DL) to improve the practice of medicine and its clinical outcomes faces a looming obstacle: model interpretation. Without description of how outputs are generated, a collaborating physician can neither resolve…

In general-purpose particle detectors, the particle-flow algorithm may be used to reconstruct a comprehensive particle-level view of the event by combining information from the calorimeters and the trackers, significantly improving the…

In the parameter space allowed by the electroweak precision measurement data, we consider the contributions of the new particles predicted by the littlest Higgs($LH$) model to the Higgs boson associated production with top quark pair in the…

We present a Machine Learning approach based on Symbolic Regression to derive, from either numerically generated or experimentally measured spectral data, closed-form expressions that model the optical properties of biological materials. To…

Machine-learning methods are gradually being adopted in a wide variety of social, economic, and scientific contexts, yet they are notorious for struggling with exact mathematics. A typical example is computer algebra, which includes tasks…

Many models beyond the Standard Model predict light and feebly interacting particles that are often long-lived. These long-lived particles (LLPs) in many cases can be produced from meson decays. In this work, we propose a simple and quick…

The top-Higgs coupling plays an important role in particle physics and cosmology. The precision measurements of this coupling can provide an insight to new physics beyond the Standard Model. In this paper, we propose to use Message Passing…

Machine-learning of atomic-scale properties amounts to extracting correlations between structure, composition and the quantity that one wants to predict. Representing the input structure in a way that best reflects such correlations makes…

The LHC has been built to understand the dynamics at the origin of the breaking of the electroweak symmetry. Weakly coupled models with a fundamental Higgs boson have focused most of the attention of the experimental searches. We will…

We comment on the Standard Model Higgs boson evidence from LHC. We propose that the new resonance at 125 GeV could be interpreted as a pseudoscalar meson with quantum number $J^{PC} = 0^{- +}$. We show that this pseudoscalar could mimic the…

Identifying governing equations for a dynamical system is a topic of critical interest across an array of disciplines, from mathematics to engineering to biology. Machine learning -- specifically deep learning -- techniques have shown their…

Recurrent neural networks (RNNs) have achieved state-of-the-art performances in many natural language processing tasks, such as language modeling and machine translation. However, when the vocabulary is large, the RNN model will become very…

We investigate the use of machine learning for solving analytic problems in theoretical physics. In particular, symbolic regression (SR) is making rapid progress in recent years as a tool to fit data using functions whose overall form is…