Domain adaptation with gradient reversal for MC/real data calibration
In the research, a new approach for finding rare events in high-energy physics was tested. As an example of physics channel the decay of \tau -> 3 \mu is taken that has been published on Kaggle within LHCb-supported challenge. The training sample consists of simulated signal and real background, so the challenge is to train classifier in such way that it picks up signal/background differences and doesn’t overfits to simulation-specific features. The approach suggested is based on cross-domain adaptation using neural networks with gradient reversal. The network architecture is a dense multi-branch structure. One branch is responsible for signal/background discrimination, the second branch helps to avoid overfitting on Monte-Carlo training dataset. The tests showed that this architecture is a robust a mechanism for choosing tradeoff between discrimination power and overfitting, moreover, it also improves the quality of the baseline prediction. Thus, this approach allowed us to train deep learning models without reducing the quality, which allow us to distinguish physical parameters, but do not allow us to distinguish simulated events from real ones. The third network branch helps to eliminate the correlation between classifier predictions and reconstructed mass of the decay, thereby making such approach highly viable for great variety of physics searches.
Autonomous taxies are in high demand for smart city scenario. Such taxies have a well specified path to travel. Therefore, these vehicles only required two important parameters. One is detection parameter and other is control parameter. Further, detection parameters require turn detection and obstacle detection. The control parameters contain steering control and speed control. In this paper a novel autonomous taxi model has been proposed for smart city scenario. Deep learning has been used to model the human driver capabilities for the autonomous taxi. A hierarchical Deep Neural Network (DNN) architecture has been utilized to train various driving aspects. In first level, the proposed DNN architecture classifies the straight and turning of road. A parallel DNN is used to detect obstacle at level one. In second level, the DNN discriminates the turning i.e. left or right for steering and speed controls. Two multi layered DNNs have been used on Nvidia Tesla K 40 GPU based system with Core i-7 processor. The mean squared error (MSE) for the detection parameters viz. speed and steering angle were 0.018 and 0.0248 percent, respectively, with 15 milli seconds of realtime response delay.
Reconstruction and identification in calorimeters of modern High Energy Physics experiments is a complicated task. Solutions are usually driven by a priori knowledge about expected properties of reconstructed objects. Such an approach is also used to distinguish single photons in the electromagnetic calorimeter of the LHCb detector on LHC from overlapping photons produced from high momentum pi0 decays. We studied an alternative solution based on applying machine learning techniques to primary calorimeter information, that are energies collected in individual cells around the energy cluster. Constructing such a discriminator from “first principles” allowed improve separation performance from 80% to 93%, that means reducing primary photons fake rate by factor of two. In presentation we discuss different approaches to the problem, architecture of the classifier, its optimization, and compare performance of the ML approach with classical one.
The production of W and Z bosons in association with jets is studied in the forward region of proton-proton collisions collected at a centre-of-mass energy of 8 TeV by the LHCb experiment, corresponding to an integrated luminosity of 1.98 ± 0.02 fb−1 . The W boson is identified using its decay to a muon and a neutrino, while the Z boson is identified through its decay to a muon pair. Total cross-sections are measured and combined into charge ratios, asymmetries, and ratios of W+jet and Z+jet production cross-sections. Differential measurements are also performed as a function of both boson and jet kinematic variables. All results are in agreement with Standard Model predictions.
The performance of machine learning methods is heavily dependent on the choice of data representation (or features) on which they are applied. The rapidly developing field of representation learning is concerned with questions surrounding how we can best learn meaningful and useful representations of data. We take a broad view of the field and include topics such as deep learning and feature learning, metric learning, compositional modeling, structured prediction, reinforcement learning, and issues regarding large-scale learning and non-convex optimization. The range of domains to which these techniques apply is also very broad, from vision to speech recognition, text understanding, gaming, music, etc.
This paper concerns discourse-new mention detection in Russian. This might be helpful for different NLP applications such as coreference resolution, protagonist identification, summarization and different tasks of information extraction to detect the mention of an entity newly introduced into discourse. In our work, we are dealing with the Russian where there is no grammatical devices, like articles in English, for the overt marking a newly introduced referent. Our aim is to check the impact of various features on this task. The focus is on specific devices for introducing a new discourse prominent referent in Russian specified in theoretical studies. We conduct a pilot study of features impact and provide a series of experiments on detecting the first mention of a referent in a non-singleton coreference chain, drawing on linguistic insights about how a prominent entity introduced into discourse is affected by structural, morphological and lexical features.
This book constitutes the refereed proceedings of the 4th International Conference on Mining Intelligence and Knowledge Exploration, MIKE 2016, held in Mexico City, Mexico, in November 2016.
The 18 full papers presented were carefully reviewed and selected from 56 submissions.
Accepted papers were grouped into various subtopics including information retrieval, machine learning, pattern recognition, knowledge discovery, classification, clustering, image processing, network security, speech processing, natural language processing, language, cognition and computation, fuzzy sets, and business intelligence.
A full amplitude analysis of Λ 0 b → J/ψ pπ− decays is performed with a data sample acquired with the LHCb detector from 7 and 8 TeV pp collisions, corresponding to an integrated luminosity of 3 fb−1 . A significantly better description of the data is achieved when, in addition to the previously observed nucleon excitations N → pπ−, either the Pc(4380)+ and Pc(4450)+ → J/ψ p states, previously observed in Λ 0 b → J/ψ pK− decays, or the Zc(4200)− → J/ψ π− state, previously reported in B0 → J/ψ K+π − decays, or all three, are included in the amplitude models. The data support a model containing all three exotic states, with a significance of more than three standard deviations. Within uncertainties, the data are consistent with the Pc(4380)+ and Pc(4450)+ production rates expected from their previous observation taking account of Cabibbo suppression.
The dynamics of a two-component Davydov-Scott (DS) soliton with a small mismatch of the initial location or velocity of the high-frequency (HF) component was investigated within the framework of the Zakharov-type system of two coupled equations for the HF and low-frequency (LF) fields. In this system, the HF field is described by the linear Schrödinger equation with the potential generated by the LF component varying in time and space. The LF component in this system is described by the Korteweg-de Vries equation with a term of quadratic influence of the HF field on the LF field. The frequency of the DS soliton`s component oscillation was found analytically using the balance equation. The perturbed DS soliton was shown to be stable. The analytical results were confirmed by numerical simulations.
Radiation conditions are described for various space regions, radiation-induced effects in spacecraft materials and equipment components are considered and information on theoretical, computational, and experimental methods for studying radiation effects are presented. The peculiarities of radiation effects on nanostructures and some problems related to modeling and radiation testing of such structures are considered.