arXiv subjects

Zhuo Li

Publications and source records attributed to Zhuo Li.

At least 181 records · Page 10Linked to original sources

arXiv2021

The HCCL Speaker Verification System for Far-Field Speaker Verification Challenge

This paper describes the systems submitted by team HCCL to the Far-Field Speaker Verification Challenge. Our previous work in the AIshell Speaker Verification Challenge 2019 shows that the powerful modeling abilities of Neural Network architectures can provide exceptional performance for this kind of task. Therefore, in this challenge, we focus on constructing deep Neural Network architectures based on TDNN, Resnet and Res2net blocks. Most of the developed systems consist of Neural Network embeddings are applied with PLDA backend. Firstly, the speed perturbation method is applied to augment data and significant performance improvements are achieved. Then, we explore the use of AMsoftmax loss function and propose to join a CE-loss branch when we train model using AMsoftmax loss. In addition, the impact of score normalization on performance is also investigated. The final system, a fusion of four systems, achieves minDCF 0.5342, EER 5.05\% on task1 eval set, and achieves minDCF 0.5193, EER 5.47\% on task3 eval set.

cs.SD↗

arXiv2021

Kilonova Emission From Black Hole-Neutron Star Mergers. II. Luminosity Function and Implications for Target-of-opportunity Observations of Gravitational-wave Triggers and Blind Searches

We present detailed simulations of black hole-neutron star (BH-NS) mergers kilonova and gamma-ray burst (GRB) afterglow and kilonova luminosity function, and discuss the detectability of electromagnetic (EM) counterpart in connection with gravitational wave (GW) detections, GW-triggered target-of-opportunity observations, and time-domain blind searches. The predicted absolute magnitude of the BH-NS kilonovae at $0.5\,{\rm days}$ after the merger falls in $[-10,-15.5]$. The simulated luminosity function contains the potential viewing-angle distribution information of the anisotropic kilonova emission. We simulate the GW detection rates, detectable distances and signal duration, for the future networks of 2nd/2.5th/3rd-generation GW detectors. BH-NSs tend to produce brighter kilonovae and afterglows if the BH has a higher aligned-spin, and a less massive NS with a stiffer EoS. The detectability of kilonova is especially sensitive to the BH spin. If BHs typically have low spins, the BH-NS EM counterparts are hard to discover. For the 2nd generation GW detector networks, a limiting magnitude of $m_{\rm limit}\sim23-24\,{\rm mag}$ is required to detect the kilonovae even if BH high spin is assumed. Thus, a plausible explanation for the lack of BH-NS associated kilonova detection during LIGO/Virgo O3 is that either there is no EM counterpart (plunging events), or the current follow-ups are too shallow. These observations still have the chance to detect the on-axis jet afterglow associated with an sGRB or an orphan afterglow. Follow-up observations can detect possible associated sGRB afterglows, from which kilonova signatures may be studied. For time-domain observations, a high-cadence search in redder filters is recommended to detect more BH-NS associated kilonovae and afterglows.

astro-ph.HE↗

arXiv2021

Overcoming Long-term Catastrophic Forgetting through Adversarial Neural Pruning and Synaptic Consolidation

Artificial neural networks face the well-known problem of catastrophic forgetting. What's worse, the degradation of previously learned skills becomes more severe as the task sequence increases, known as the long-term catastrophic forgetting. It is due to two facts: first, as the model learns more tasks, the intersection of the low-error parameter subspace satisfying for these tasks becomes smaller or even does not exist; second, when the model learns a new task, the cumulative error keeps increasing as the model tries to protect the parameter configuration of previous tasks from interference. Inspired by the memory consolidation mechanism in mammalian brains with synaptic plasticity, we propose a confrontation mechanism in which Adversarial Neural Pruning and synaptic Consolidation (ANPyC) is used to overcome the long-term catastrophic forgetting issue. The neural pruning acts as long-term depression to prune task-irrelevant parameters, while the novel synaptic consolidation acts as long-term potentiation to strengthen task-relevant parameters. During the training, this confrontation achieves a balance in that only crucial parameters remain, and non-significant parameters are freed to learn subsequent tasks. ANPyC avoids forgetting important information and makes the model efficient to learn a large number of tasks. Specifically, the neural pruning iteratively relaxes the current task's parameter conditions to expand the common parameter subspace of the task; the synaptic consolidation strategy, which consists of a structure-aware parameter-importance measurement and an element-wise parameter updating strategy, decreases the cumulative error when learning new tasks. The full source code is available at https://github.com/GeoX-Lab/ANPyC.

cs.LG↗

arXiv2021

A Search-Based Testing Framework for Deep Neural Networks of Source Code Embedding

Over the past few years, deep neural networks (DNNs) have been continuously expanding their real-world applications for source code processing tasks across the software engineering domain, e.g., clone detection, code search, comment generation. Although quite a few recent works have been performed on testing of DNNs in the context of image and speech processing, limited progress has been achieved so far on DNN testing in the context of source code processing, that exhibits rather unique characteristics and challenges. In this paper, we propose a search-based testing framework for DNNs of source code embedding and its downstream processing tasks like Code Search. To generate new test inputs, we adopt popular source code refactoring tools to generate the semantically equivalent variants. For more effective testing, we leverage the DNN mutation testing to guide the testing direction. To demonstrate the usefulness of our technique, we perform a large-scale evaluation on popular DNNs of source code processing based on multiple state-of-the-art code embedding methods (i.e., Code2vec, Code2seq and CodeBERT). The testing results show that our generated adversarial samples can on average reduce the performance of these DNNs from 5.41% to 9.58%. Through retraining the DNNs with our generated adversarial samples, the robustness of DNN can improve by 23.05% on average. The evaluation results also show that our adversarial test generation strategy has the least negative impact (median of 3.56%), on the performance of the DNNs for regular test data, compared to the other methods.

cs.SE↗

arXiv2020

Kernelized Multiview Subspace Analysis by Self-weighted Learning

With the popularity of multimedia technology, information is always represented or transmitted from multiple views. Most of the existing algorithms are graph-based ones to learn the complex structures within multiview data but overlooked the information within data representations. Furthermore, many existing works treat multiple views discriminatively by introducing some hyperparameters, which is undesirable in practice. To this end, abundant multiview based methods have been proposed for dimension reduction. However, there are still no research to leverage the existing work into a unified framework. To address this issue, in this paper, we propose a general framework for multiview data dimension reduction, named Kernelized Multiview Subspace Analysis (KMSA). It directly handles the multi-view feature representation in the kernel space, which provides a feasible channel for direct manipulations on multiview data with different dimensions. Meanwhile, compared with those graph-based methods, KMSA can fully exploit information from multiview data with nothing to lose. Furthermore, since different views have different influences on KMSA, we propose a self-weighted strategy to treat different views discriminatively according to their contributions. A co-regularized term is proposed to promote the mutual learning from multi-views. KMSA combines self-weighted learning with the co-regularized term to learn appropriate weights for all views. We also discuss the influence of the parameters in KMSA regarding the weights of multi-views. We evaluate our proposed framework on 6 multiview datasets for classification and image retrieval. The experimental results validate the advantages of our proposed method.

cs.LG↗

arXiv2020

Limiting Superluminal Neutrino Velocity and Lorentz Invariance Violation by Neutrino Emission from the Blazar TXS 0506+056

The detection of high-energy neutrino coincident with the blazar TXS 0506+056 provides a unique opportunity to test Lorentz invariance violation (LIV) in the neutrino sector. Thanks to the precisely measured redshift, i.e., $z=0.3365$, the comoving distance of the neutrino source is determined. In this work, we obtain and discuss the constraints on the superluminal neutrino velocity $δ_ν$ and the LIV by considering the energy loss of superluminal neutrino during propagation. Given superluminal electron velocity ($δ_e \ge 0$), a very stringent constraint on superluminal neutrino velocity can be reached, i.e., $δ_ν\lesssim 1.3\times 10^{-18}$, corresponding to the quantum gravity (QG) scale $M_{\rm QG,1} \gtrsim 5.7 \times 10^{3} M_{\rm Pl}$ and $M_{\rm QG,2} \gtrsim 9.3 \times 10^{-6} M_{\rm Pl}$ for linear (quadratic) LIV, which are $\sim 12$ orders of magnitude tighter for linear LIV and $\sim 9$ orders tighter for quadratic LIV compared to the time-of-flight constraint from MeV neutrinos of SN 1987A. While given the subluminal electron velocity, a weaker constraint on the superluminal neutrino velocity is obtained, i.e., $δ_ν\lesssim 8 \times 10^{-17}$, which is consistent with the conclusions of previous works. We also study the neutrino detection probability due to the distortion of neutrino spectral shape during propagation, which gives slightly weaker constraints than above by a factor of $\sim2$.

astro-ph.HE↗

arXiv2020

Robust Handwriting Recognition with Limited and Noisy Data

Despite the advent of deep learning in computer vision, the general handwriting recognition problem is far from solved. Most existing approaches focus on handwriting datasets that have clearly written text and carefully segmented labels. In this paper, we instead focus on learning handwritten characters from maintenance logs, a constrained setting where data is very limited and noisy. We break the problem into two consecutive stages of word segmentation and word recognition respectively and utilize data augmentation techniques to train both stages. Extensive comparisons with popular baselines for scene-text detection and word recognition show that our system achieves a lower error rate and is more suited to handle noisy and difficult documents

cs.CV↗

arXiv2020

Kilonova Emission From Black Hole-Neutron Star Mergers. I. Viewing-Angle-Dependent Lightcurves

In this paper, we present a numerical method to study the predicted lightcurves as a function of viewing angle. We extrapolate the fitting formulae for the mass and velocity of tidal dynamical ejecta across a wide range of mass ratio validated with 66 simulations and use them in the calculations of the kilonova lightcurves. The calculated peak luminosity of a BH-NS merger kilonova is typically about a few times $10^{41}\ {\rm erg\ s^{-1}}$, which is always $\lesssim4.5\times10^{41}\ {\rm erg\ s^{-1}}$. This corresponds to the AB absolute magnitudes fainter than $\sim -15\ {\rm mag}$ in optical and $\sim -16\ {\rm mag}$ in infrared. Since the projected photosphere area of the dynamical ejecta is much larger than that of the disk wind outflows, the dynamical ejecta usually contribute to the majority of the kilonova emission from BH-NS mergers. The fitted blackbody temperature and the shape of the observed multi-band lightcurves are insensitive to the line of sight. The peak time of the observed multi-band lightcurves, affected by the light propagation effect, is related to the relative motion direction between the dynamical ejecta and the observer. The observed luminosity varies with the projected photosphere area determined by the viewing angles. However, the predicted peak luminosity only varies by a factor of $\sim (2 - 3)$ (or by $\sim1\ {\rm mag}$) for different viewing angles. When the short-duration gamma-ray burst afterglow is taken into account, for an on-axis geometry, the kilonova emission is usually outshone by the afterglow emission and can be only observed in the redder bands, especially in the $K$-band at late times. Compared with GW170817/AT2017gfo, the BH-NS merger kilonovae are optically dim but possibly infrared bright. At the same epoch after the merger, the blackbody fitting temperature of the BH-NS merger kilonovae is lower than that of GW170817/AT2017gfo.

astro-ph.HE↗

arXiv2020

A Machine Learning Framework for Data Ingestion in Document Images

Paper documents are widely used as an irreplaceable channel of information in many fields, especially in financial industry, fostering a great amount of demand for systems which can convert document images into structured data representations. In this paper, we present a machine learning framework for data ingestion in document images, which processes the images uploaded by users and return fine-grained data in JSON format. Details of model architectures, design strategies, distinctions with existing solutions and lessons learned during development are elaborated. We conduct abundant experiments on both synthetic and real-world data in State Street. The experimental results indicate the effectiveness and efficiency of our methods.

cs.CV↗

arXiv2020

Cooperative Source Seeking via Networked Multi-vehicle Systems

This paper studies the cooperative source seeking problem via a networked multi-vehicle system. In contrast to existing literature, the multi-vehicle system is controlled to the source position that maximizes aggregated multiple unknown scalar fields and each sensor-enabled vehicle only samples measurements of one scalar field. Thus, a single vehicle is unable to localize the source and has to cooperate with its neighboring vehicles. By jointly exploiting the ideas of the consensus algorithm and the stochastic extremum seeking (ES), this paper proposes novel distributed stochastic ES controllers, which are gradient-free and do not need any absolute information, such that the multi-vehicle system simultaneously approaches the source position. The effectiveness of the proposed controllers is proved for quadratic scalar fields. Finally, illustrative examples are included to validate the theoretical results.

eess.SP↗

arXiv2020

Secondary-electron radiation accompanying hadronic GeV-TeV gamma-rays from supernova remnants

The synchrotron radiation from secondary electrons and positrons (SEPs) generated by hadronic interactions in the shock of supernova remnant (SNR) could be a distinct evidence of cosmic ray (CR) production in SNR shocks. Here we provide a method where the observed gamma-ray flux from SNRs, created by pion decays, is directly used to derive the SEP distribution and hence the synchrotron spectrum. We apply the method to three gamma-ray bright SNRs. In the young SNR RX J1713.7-3946, if the observed GeV-TeV gamma-rays are of hadronic origin and the magnetic field in the SNR shock is $B\gtrsim 0.5$mG, the SEPs may produce a spectral bump at $10^{-5}-10^{-2}$eV, exceeding the predicted synchrotron component of the leptonic model, and a soft spectral tail at $\gtrsim 100$keV, distinct from the hard spectral slope in the leptonic model. In the middle-aged SNRs IC443 and W44, if the observed gamma-rays are of hadronic origin, the SEP synchrotron radiation with $B\sim 400 - 500 μ$G can well account for the observed radio flux and spectral slopes, supporting the hadronic origin of gamma-rays. Future microwave to far-infrared and hard X-ray (>100keV) observations are encouraged to constraining the SEP radiation and the gamma-ray origin in SNRs.

astro-ph.HE↗

arXiv2019

Prediction and Communication Co-design for Ultra-Reliable and Low-Latency Communications

Ultra-reliable and low-latency communications (URLLC) are considered as one of three new application scenarios in the fifth generation cellular networks. In this work, we aim to reduce the user experienced delay through prediction and communication co-design, where each mobile device predicts its future states and sends them to a data center in advance. Since predictions are not error-free, we consider prediction errors and packet losses in communications when evaluating the reliability of the system. Then, we formulate an optimization problem that maximizes the number of URLLC services supported by the system by optimizing time and frequency resources and the prediction horizon. Simulation results verify the effectiveness of the proposed method, and show that the tradeoff between user experienced delay and reliability can be improved significantly via prediction and communication co-design. Furthermore, we carried out an experiment on the remote control in a virtual factory, and validated our concept on prediction and communication co-design with the practical mobility data generated by a real tactile device.

eess.SP↗

arXiv2019

Optimization-based Control for Bearing-only Target Search with a Mobile Vehicle

This work aims to design an optimization-based controller for a discrete-time Dubins vehicle to approach a target with unknown position as fast as possible by only using bearing measurements. To this end, we propose a bi-objective optimization problem, which jointly considers the performance of estimating the unknown target position and controlling the mobile vehicle to a known position, and then adopt a weighted sum method with normalization to solve it. The controller is given based on the solution of the optimization problem in ties with a least-square estimate of the target position. Moreover, the controller does not need the vehicle's global position information. Finally, simulation results are included to validate the effectiveness of the proposed controller.

eess.SY↗

arXiv2019

A hadronuclear interpretation of a high-energy neutrino event coincident with a blazar flare

Although many high-energy neutrinos detected by the IceCube telescope are believed to have anextraterrestrial origin, their astrophysical sources remain a mystery. Recently, an unprecedenteddiscovery of a high-energy muon neutrino event coincident with a multiwavelength flare from ablazar, TXS 0506+056, shed some light on the origin of the neutrinos. It is usually believed that ablazar is produced by a relativistic jet launched from an accreting supermassive black hole (SMBH).Here we show that the high-energy neutrino event can be interpreted by the inelastic hadronuclearinteractions between the accelerated cosmic-ray protons in the relativistic jet and the dense gasclouds in the vicinity of the SMBH. Such a scenario only requires a moderate proton power in thejet, which could be much smaller than that required in the conventional hadronic model whichinstead calls upon the photomeson process. Meanwhile, the flux of the multiwavelength flare fromthe optical to gamma-ray band can be well explained by invoking a second radiation zone in thejet at a larger distance to the SMBH. In our model, the neutrino emission lasts a shorter time thanthe multiwavelength flare so the neutrino event is not necessarily correlated with the flare but it is probably accompanied by a spectrum hardening above a few GeV.

astro-ph.HE↗

arXiv2019

Understanding the Importance of Single Directions via Representative Substitution

Understanding the internal representations of deep neural networks (DNNs) is crucal to explain their behavior. The interpretation of individual units, which are neurons in MLPs or convolution kernels in convolutional networks, has been paid much attention given their fundamental role. However, recent research (Morcos et al. 2018) presented a counterintuitive phenomenon, which suggests that an individual unit with high class selectivity, called interpretable units, has poor contributions to generalization of DNNs. In this work, we provide a new perspective to understand this counterintuitive phenomenon, which makes sense when we introduce Representative Substitution (RS). Instead of individually selective units with classes, the RS refers to the independence of a unit's representations in the same layer without any annotation. Our experiments demonstrate that interpretable units have high RS which are not critical to network's generalization. The RS provides new insights into the interpretation of DNNs and suggests that we need to focus on the independence and relationship of the representations.

cs.LG↗

arXiv2019

Transient High-energy Gamma-rays and Neutrinos from Nearby Type II Supernovae

The dense wind environment (or circumstellar medium) may be ubiquitous for the regular Type II supernovae (SNe) before the explosion, the interaction of which with the SN ejecta could result in a wind breakout event. The shock generated by the interaction of the SN ejecta and the wind can accelerate the protons and subsequently the high-energy gamma-rays and neutrinos could arise from the inelastic pp collisions. In this work, we present the detailed calculations of gamma-ray and neutrino production for the regular Type II SNe. The calculation is executed by applying time-dependent evolutions of dynamic and proton distribution so that the emission could be shown at different times. Our results show, for the SN 2013fs-like wind environment, the multi-GeV and ~ few-100 TeV gamma-rays are detectable with a time window of several days at <~ 2-3 Mpc by Fermi/LAT and CTA during the ejecta-wind interaction, respectively, and can be detected at a further distance if the wind environment is denser. Besides, we found the contribution of the wind breakouts of regular Type II SNe to diffuse neutrino flux is subdominant by assuming all Type II SNe are SN 2013fs-like, whereas for a denser wind environment the contribution could be conspicuous above 300TeV.

astro-ph.HE↗

arXiv2018

PeV neutrinos from wind breakouts of type II supernovae

Recently, the rapid multiwavelength photometry and flash spectra of supernova (SN) 2013fs imply that the progenitor stars of regular type II SNe (SNe II) might be commonly surrounded with a confined dense stellar wind ejected by themselves with large mass loss rate few years before the SNe. Based on the assumption that the pre-SN progenitor stars of SNe II have a SN 2013fs-like wind, with mass loss rate $\dot{M}\sim3\times10^{-3}(v_w/100\rm km\,s^{-1})M_\odot\rm yr^{-1}$, we investigate the neutrino emission during the wind breakouts of SN shocks. We find that the regular SNe II can convert a fraction $\sim10^{-3}$ of their bulk kinetic energy into neutrino emission, which can contribute a significant fraction of the IceCube-detected neutrino flux at $\ga300$ TeV. Moreover, the $\la200$~TeV IceCube neutrinos can be accounted for by cosmic rays produced by the shocks of all SN remnants, losing energy in their host galaxies, i.e., starburst galaxies. The future follow-up observations of neutrinos by Gen2 and gamma-rays by CTA and LHAASO from nearby individual SNe II, within weeks after the explosions, will test this model.

astro-ph.HE↗

arXiv2018

Understanding the Importance of Single Directions via Representative Substitution

cs.CV↗