Invariant representation driven neural classifier for anti-QCD jet tagging

W vs. QCD Jet Tagging at the Large Hadron Collider

High energy collisions of protons at the Large Hadron Collider (LHC) produce massive particles such as W, Z, Higgs bosons, and top quarks. A key task in the search for physics beyond the standard model is to study the kinematic configurations of these heavy particles. The massive particles are observed indirectly by the energy signature they generate. The heavy particles decay into quarks and g...

Jet Constituents for Deep Neural Network Based Top Quark Tagging

Abstract Recent literature on deep neural networks for tagging of highly energetic jets resulting from top quark decays has focused on image based techniques or multivariate approaches using high level jet substructure variables. Here a sequential approach to this task is taken by using an ordered sequence of jet constituents as training inputs. Unlike previous approaches, this strategy does no...

Isolating Purely Leptonic Signals for Strong W Scattering Using Anti-tagging, Jet-tagging and Lepton Isolation*

We explore in depth several techniques for detecting the Z+1+ mass spectrum coming from W+ W+ scattering at a hadron collider. We focus on the signal, due to enhanced production of longitudinally polarized W+‘s, that arises in the Standard Model when the Higgs boson has mass ;L 1 TeV. We demonstrate that anti-tagging against energetic centrally produced jets must be combined either with our ear...

Learning classifier systems with neural network representation

Representation Theory and Invariant Neural Networks

A feedforward neural network is a computational device used for pattern recognition. In many recognition problems, certain transformations exist which, when applied to a pattern, leave its classification unchanged. Invariance under a given group of transformations is therefore typically a desirable property of pattern classifiers. In this paper, we present a methodology, based on representation...