arXiv subjects

Lei Wang

Publications and source records attributed to Lei Wang.

At least 1,009 records · Page 56Linked to original sources

arXiv2020

SNEAP: A Fast and Efficient Toolchain for Mapping Large-Scale Spiking Neural Network onto NoC-based Neuromorphic Platform

Spiking neural network (SNN), as the third generation of artificial neural networks, has been widely adopted in vision and audio tasks. Nowadays, many neuromorphic platforms support SNN simulation and adopt Network-on-Chips (NoC) architecture for multi-cores interconnection. However, interconnection brings huge area overhead to the platform. Moreover, run-time communication on the interconnection has a significant effect on the total power consumption and performance of the platform. In this paper, we propose a toolchain called SNEAP for mapping SNNs to neuromorphic platforms with multi-cores, which aims to reduce the energy and latency brought by spike communication on the interconnection. SNEAP includes two key steps: partitioning the SNN to reduce the spikes communicated between partitions, and mapping the partitions of SNN to the NoC to reduce average hop of spikes under the constraint of hardware resources. SNEAP can reduce more spikes communicated on the interconnection of NoC and spend less time than other toolchains in the partitioning phase. Moreover, the average hop of spikes is reduced more by SNEAP within a time period, which effectively reduces the energy and latency on the NoC-based neuromorphic platform. The experimental results show that SNEAP can achieve 418x reduction in end-to-end execution time, and reduce energy consumption and spike latency, on average, by 23% and 51% respectively, compared with SpiNeMap.

cs.DC↗

arXiv2020

Progressive Cross-camera Soft-label Learning for Semi-supervised Person Re-identification

In this paper, we focus on the semi-supervised person re-identification (Re-ID) case, which only has the intra-camera (within-camera) labels but not inter-camera (cross-camera) labels. In real-world applications, these intra-camera labels can be readily captured by tracking algorithms or few manual annotations, when compared with cross-camera labels. In this case, it is very difficult to explore the relationships between cross-camera persons in the training stage due to the lack of cross-camera label information. To deal with this issue, we propose a novel Progressive Cross-camera Soft-label Learning (PCSL) framework for the semi-supervised person Re-ID task, which can generate cross-camera soft-labels and utilize them to optimize the network. Concretely, we calculate an affinity matrix based on person-level features and adapt them to produce the similarities between cross-camera persons (i.e., cross-camera soft-labels). To exploit these soft-labels to train the network, we investigate the weighted cross-entropy loss and the weighted triplet loss from the classification and discrimination perspectives, respectively. Particularly, the proposed framework alternately generates progressive cross-camera soft-labels and gradually improves feature representations in the whole learning course. Extensive experiments on five large-scale benchmark datasets show that PCSL significantly outperforms the state-of-the-art unsupervised methods that employ labeled source domains or the images generated by the GAN-based models. Furthermore, the proposed method even has a competitive performance with respect to deep supervised Re-ID methods.

cs.CV↗

arXiv2020

Method for Extracting Patterns of Coordinated Network Attacks on Electric Power CPS based on Temporal-Topological Correlation

In the analysis of coordinated network attacks on electric power cyber-physical system (CPS), it is difficult to restore the complete attack path, and the intent of the attack cannot be identified automatically. A method is therefore proposed for the extracting patterns of coordinated network attacks on electric power CPS based on temporal-topological correlation. First, the attack events are aggregated according to the alarm log of the cyber space, and a temporal-causal Bayesian network-based cyber attack recognition algorithm is proposed to parse out the cyber attack sequences of the same attacker. Then, according to the characteristic curves of different attack measurement data in physical space, a combination of physical attack event criteria algorithm is designed to distinguish the types of physical attack events. Finally, physical attack events and cyber attack sequences are matched via temporal-topological correlation, frequent patterns of attack sequences are extracted, and hidden multi-step attack patterns are found from scattered grid measurement data and information from alarm logs. The effectiveness and efficiency of the proposed method are verified by the testbed at Mississippi State University.

cs.CR↗

arXiv2020

The Collectivity of Heavy Mesons in Proton-Nucleus Collisions

Using a model based on the Color Glass Condensate framework and the dilute-dense factorization, we systematically study the azimuthal angular correlations between a heavy flavor meson and a light reference particle in proton-nucleus collisions. The obtained second harmonic coefficients (also known as the elliptic flows) for $J/ψ$ and $D^0$ agree with recent experimental data from the LHC. We also provide predictions for the elliptic flows of $Υ$ and $B$ meson, which can be measured in the near future at the LHC. This work can shed light on the physics origin of the collectivity phenomenon in the collisions of small systems.

hep-ph↗

arXiv2020

Semi-Inclusive Jet Functions and Jet Substructure in $J_{E_T}^{(I)}$ and $J_{E_T}^{(II)}$ Algorithms

Within the framework of Soft Collinear Effective Theory, we present calculations of semi-inclusive jet functions and fragmenting jet functions at next-to-leading order (NLO) for both quark- and gluon-initiated jets, for jet algorithms of $J_{E_T}^{(I)}$ and $J_{E_T}^{(II)}$ where one maximizes a suitable jet function. We demonstrate the consistency of the obtained results with the standard perturbative QCD calculations for $J_{E_T}^{(I)}$ algorithm, while the results for fragmenting jet functions with the $J_{E_T}^{(II)}$ algorithm are new. The renormalization group (RG) equation for both semi-inclusive jet functions and fragmenting jet functions are derived and shown to follow the time-like DGLAP evolution equations, independent of specific jet algorithms. The RG equation can be used to resum single logarithms of the jet size parameter $β$ for highly collimated jets in these algorithms where $β\gg 1$.

hep-ph↗

arXiv2020

Industrial Scale Privacy Preserving Deep Neural Network

Deep Neural Network (DNN) has been showing great potential in kinds of real-world applications such as fraud detection and distress prediction. Meanwhile, data isolation has become a serious problem currently, i.e., different parties cannot share data with each other. To solve this issue, most research leverages cryptographic techniques to train secure DNN models for multi-parties without compromising their private data. Although such methods have strong security guarantee, they are difficult to scale to deep networks and large datasets due to its high communication and computation complexities. To solve the scalability of the existing secure Deep Neural Network (DNN) in data isolation scenarios, in this paper, we propose an industrial scale privacy preserving neural network learning paradigm, which is secure against semi-honest adversaries. Our main idea is to split the computation graph of DNN into two parts, i.e., the computations related to private data are performed by each party using cryptographic techniques, and the rest computations are done by a neutral server with high computation ability. We also present a defender mechanism for further privacy protection. We conduct experiments on real-world fraud detection dataset and financial distress prediction dataset, the encouraging results demonstrate the practicalness of our proposal.

cs.LG↗

arXiv2020

Extended Batch Normalization

Batch normalization (BN) has become a standard technique for training the modern deep networks. However, its effectiveness diminishes when the batch size becomes smaller, since the batch statistics estimation becomes inaccurate. That hinders batch normalization's usage for 1) training larger model which requires small batches constrained by memory consumption, 2) training on mobile or embedded devices of which the memory resource is limited. In this paper, we propose a simple but effective method, called extended batch normalization (EBN). For NCHW format feature maps, extended batch normalization computes the mean along the (N, H, W) dimensions, as the same as batch normalization, to maintain the advantage of batch normalization. To alleviate the problem caused by small batch size, extended batch normalization computes the standard deviation along the (N, C, H, W) dimensions, thus enlarges the number of samples from which the standard deviation is computed. We compare extended batch normalization with batch normalization and group normalization on the datasets of MNIST, CIFAR-10/100, STL-10, and ImageNet, respectively. The experiments show that extended batch normalization alleviates the problem of batch normalization with small batch size while achieving close performances to batch normalization with large batch size.

cs.CV↗

arXiv2020

Exploration of Surgeons' Natural Skills for Robotic Catheterization

Despite having the robotic catheter systems which have recently emerged as safe way of performing cardiovascular interventions, a number of important challenges are yet to be investigated. One of them is exploration of surgeons' natural skills during vascular catheterization with robotic systems. In this study, surgeons' natural hand motions were investigated for identification of four basic movements used for intravascular catheterization. Controlled experiment was setup to acquire surface electromyography (sEMG) signals from six muscles that are innervated when a subject with catheterization skills made the four movements in open settings. k-means and k-NN models were implemented over average EMG and root means square features to uniquely identify the movements. The result shows great potentials of sEMG analysis towards designing intelligent cyborg control for safe and efficient robotic catheterization.

physics.med-ph↗

arXiv2020

AIBench: An Agile Domain-specific Benchmarking Methodology and an AI Benchmark Suite

Domain-specific software and hardware co-design is encouraging as it is much easier to achieve efficiency for fewer tasks. Agile domain-specific benchmarking speeds up the process as it provides not only relevant design inputs but also relevant metrics, and tools. Unfortunately, modern workloads like Big data, AI, and Internet services dwarf the traditional one in terms of code size, deployment scale, and execution path, and hence raise serious benchmarking challenges. This paper proposes an agile domain-specific benchmarking methodology. Together with seventeen industry partners, we identify ten important end-to-end application scenarios, among which sixteen representative AI tasks are distilled as the AI component benchmarks. We propose the permutations of essential AI and non-AI component benchmarks as end-to-end benchmarks. An end-to-end benchmark is a distillation of the essential attributes of an industry-scale application. We design and implement a highly extensible, configurable, and flexible benchmark framework, on the basis of which, we propose the guideline for building end-to-end benchmarks, and present the first end-to-end Internet service AI benchmark. The preliminary evaluation shows the value of our benchmark suite---AIBench against MLPerf and TailBench for hardware and software designers, micro-architectural researchers, and code developers. The specifications, source code, testbed, and results are publicly available from the web site \url{http://www.benchcouncil.org/AIBench/index.html}.

cs.PF↗

arXiv2020

The three-level coupled Maxwell-Bloch equations: rogue waves, semirational rogue waves and W-shaped solitons

In this paper the coupled Maxwell-Bloch equations which describe the propagation of two optical pulses in an optical medium with coherent three-level atoms are studied by Darboux transformation. The general nth-order rogue wave solution involving two different choices of multiple roots for the spectral characteristic equation and the multiparametric nth-order semirational solution are both obtained in terms of Schur polynomials. The explicit rogue wave solutions and semirational solutions from first to second order are provided. In contrast to the known Peregrine soliton, dark and four-petaled structures, some unusual patterns such as triple-hole, twisted-pair, composite four-petaled and composite dark rogue waves are put forward. Moreover, the interaction between dark-bright soliton and dark rogue wave and interaction between breather and dark rogue wave are shown. Further, the higher-order nonlinear superposition modes which feature triple and quadruple temporal-spatial distributions are presented. Finally, the state transition between rogue wave and W-shaped soliton is found where the modulation instability growth rate tends to zero under the low perturbation frequency. Particularly, the dark and double-peak W-shaped solitons are examined.

nlin.SI↗

arXiv2020

Effective classical correspondence of the Mott transition

We derive an effective classical model to describe the Mott transition of the half-filled one-band Hubbard model in the framework of the dynamical mean-field theory with hybridization expansion of the continuous time quantum Monte Carlo. We find a simple two-body interaction of exponential form and reveal a classical correspondence of the Mott transition driven by a logarithmically divergent interaction length. Our work provides an alternative angle to view the Mott physics and suggests a renewed possibility to extend the application of the quantum-to-classical mapping in understanding condensed matter physics

cond-mat.str-el↗

arXiv2020

Artificial Neural Network Approach to the Analytic Continuation Problem

Inverse problems are encountered in many domains of physics, with analytic continuation of the imaginary Green's function into the real frequency domain being a particularly important example. However, the analytic continuation problem is ill defined and currently no analytic transformation for solving it is known. We present a general framework for building an artificial neural network (ANN) that solves this task with a supervised learning approach. Application of the ANN approach to quantum Monte Carlo calculations and simulated Green's function data demonstrates its high accuracy. By comparing with the commonly used maximum entropy approach, we show that our method can reach the same level of accuracy for low-noise input data, while performing significantly better when the noise strength increases. The computational cost of the proposed neural network approach is reduced by almost three orders of magnitude compared to the maximum entropy method

physics.comp-ph↗

arXiv2020

Asymmetric Distribution Measure for Few-shot Learning

The core idea of metric-based few-shot image classification is to directly measure the relations between query images and support classes to learn transferable feature embeddings. Previous work mainly focuses on image-level feature representations, which actually cannot effectively estimate a class's distribution due to the scarcity of samples. Some recent work shows that local descriptor based representations can achieve richer representations than image-level based representations. However, such works are still based on a less effective instance-level metric, especially a symmetric metric, to measure the relations between query images and support classes. Given the natural asymmetric relation between a query image and a support class, we argue that an asymmetric measure is more suitable for metric-based few-shot learning. To that end, we propose a novel Asymmetric Distribution Measure (ADM) network for few-shot learning by calculating a joint local and global asymmetric measure between two multivariate local distributions of queries and classes. Moreover, a task-aware Contrastive Measure Strategy (CMS) is proposed to further enhance the measure function. On popular miniImageNet and tieredImageNet, we achieve $3.02\%$ and $1.56\%$ gains over the state-of-the-art method on the $5$-way $1$-shot task, respectively, validating our innovative design of asymmetric distribution measures for few-shot learning.

cs.CV↗

arXiv2020

Performance of Wireless Optical Communication With Reconfigurable Intelligent Surfaces and Random Obstacles

It is difficult for free space optical communication to be applied in mobile communication due to the obstruction of obstacles in the environment, which is expected to be solved by reconfigurable intelligent surface technology. The reconfigurable intelligent surface is a new type of digital coding meta-materials, which can reflect, compute and program electromagnetic and optical waves in real time. We purpose a controllable multi-branch wireless optical communication system based on the optical reconfigurable intelligent surface technology. By setting up multiple optical reconfigurable intelligent surface in the environment, multiple artificial channels are built to improve system performance and to reduce the outage probability. Three factors affecting channel coefficients are investigated in this paper, which are beam jitter, jitter of the reconfigurable intelligent surface and the probability of obstruction. Based on the model, we derive the closed-form probability density function of channel coefficients, the asymptotic system's average bit error rate and outage probability for systems with single and multiple branches. It is revealed that the probability density function contains an impulse function, which causes irreducible error rate and outage probability floors. Numerical results indicate that compared with free-space optical communication systems with single direct path, the performance of the multi-branch system is improved and the outage probability is reduced.

eess.SY↗

arXiv2019

Gate-Tunable Graphene Hall Sensors with High Magnetic Field Sensitivity

Solid-state magnetic field sensors are important to both modern electronics and fundamental materials science. Many types of these sensors maintain high sensitivity only in a limited range of temperature and background magnetic field, but Hall-effect sensors are in principle able to operate over a broad range of these conditions. Here, we fabricate and characterize micrometer-scale graphene Hall sensors demonstrating high magnetic field sensitivity from liquid-helium to room temperature and in background magnetic field up to several Tesla. By tuning the charge carrier density with an electrostatic gate, we optimize the magnetic field sensitivity for different working conditions. From measurements of the Hall coefficient and the Hall voltage noise at 1 kHz, we estimate an optimum magnetic field sensitivity of 80 nT Hz$^{-1/2}$ at 4.2 K, 700 nT Hz$^{-1/2}$ at room temperature, and 3 $μ$T Hz$^{-1/2}$ in 3 T background magnetic field at 4.2 K. Our devices perform competitively with the best existing Hall sensor technologies at room temperature, outperform any Hall sensors reported in the literature at 4.2 K, and demonstrate high sensitivity for the first time in a few Tesla applied magnetic field.

cond-mat.mes-hall↗

arXiv2019

Solving Quantum Statistical Mechanics with Variational Autoregressive Networks and Quantum Circuits

We extend the ability of unitary quantum circuits by interfacing it with classical autoregressive neural networks. The combined model parametrizes a variational density matrix as a classical mixture of quantum pure states, where the autoregressive network generates bitstring samples as input states to the quantum circuit. We devise an efficient variational algorithm to jointly optimize the classical neural network and the quantum circuit for quantum statistical mechanics problems. One can obtain thermal observables such as the variational free energy, entropy, and specific heat. As a by product, the algorithm also gives access to low energy excitation states. We demonstrate applications to thermal properties and excitation spectra of the quantum Ising model with resources that are feasible on near-term quantum computers.

quant-ph↗

arXiv2019

ICDAR 2019 Robust Reading Challenge on Reading Chinese Text on Signboard

Chinese scene text reading is one of the most challenging problems in computer vision and has attracted great interest. Different from English text, Chinese has more than 6000 commonly used characters and Chinesecharacters can be arranged in various layouts with numerous fonts. The Chinese signboards in street view are a good choice for Chinese scene text images since they have different backgrounds, fonts and layouts. We organized a competition called ICDAR2019-ReCTS, which mainly focuses on reading Chinese text on signboard. This report presents the final results of the competition. A large-scale dataset of 25,000 annotated signboard images, in which all the text lines and characters are annotated with locations and transcriptions, were released. Four tasks, namely character recognition, text line recognition, text line detection and end-to-end recognition were set up. Besides, considering the Chinese text ambiguity issue, we proposed a multi ground truth (multi-GT) evaluation method to make evaluation fairer. The competition started on March 1, 2019 and ended on April 30, 2019. 262 submissions from 46 teams are received. Most of the participants come from universities, research institutes, and tech companies in China. There are also some participants from the United States, Australia, Singapore, and Korea. 21 teams submit results for Task 1, 23 teams submit results for Task 2, 24 teams submit results for Task 3, and 13 teams submit results for Task 4. The official website for the competition is http://rrc.cvc.uab.es/?ch=12.

cs.CV↗

arXiv2019

Application of Word2vec in Phoneme Recognition

In this paper, we present how to hybridize a Word2vec model and an attention-based end-to-end speech recognition model. We build a phoneme recognition system based on Listen, Attend and Spell model. And the phoneme recognition model uses a word2vec model to initialize the embedding matrix for the improvement of the performance, which can increase the distance among the phoneme vectors. At the same time, in order to solve the problem of overfitting in the 61 phoneme recognition model on TIMIT dataset, we propose a new training method. A 61-39 phoneme mapping comparison table is used to inverse map the phonemes of the dataset to generate more 61 phoneme training data. At the end of training, replace the dataset with a standard dataset for corrective training. Our model can achieve the best result under the TIMIT dataset which is 16.5% PER (Phoneme Error Rate).

cs.CL↗