arXiv subjects

Xiao Wang

Publications and source records attributed to Xiao Wang.

At least 703 records · Page 39Linked to original sources

arXiv2019

Microwave Integrated Circuits Design with Relational Induction Neural Network

The automation design of microwave integrated circuits (MWIC) has long been viewed as a fundamental challenge for artificial intelligence owing to its larger solution space and structural complexity than Go. Here, we developed a novel artificial agent, termed Relational Induction Neural Network, that can lead to an automotive design of MWIC and avoid brute-force computing to examine every possible solution, which is a significant breakthrough in the field of electronics. Through the experiments on microwave transmission line circuit, filter circuit and antenna circuit design tasks, strongly competitive results are obtained respectively. Compared with the traditional reinforcement learning method, the learning curve shows that the proposed architecture is able to quickly converge to the pre-designed MWIC model and the convergence rate is up to four orders of magnitude. This is the first study which has been shown that an agent through training or learning to automatically induct the relationship between MWIC's structures without incorporating any of the additional prior knowledge. Notably, the relationship can be explained in terms of the MWIC theory and electromagnetic field distribution. Our work bridges the divide between artificial intelligence and MWIC and can extend to mechanical wave, mechanics and other related fields.

eess.SP↗

arXiv2018

Two and three photon excited luminescence of single gold nanoparticles: Switching between plasmon- and electron-hole-pair emission by ultrashort laser pulses

In this work we use femtosecond laser pulses of 800 nm wavelength to excite and characterize the multiphoton luminescence emission of single gold nanoparticles. For excitation with 100 fs laser pulses we observe a two and three photon emission dominated by radiative electron hole pair recombination, while the emission is caused by radiative plasmon decay for excitation with 500 fs pulses. For single gold nanorods with different aspect ratios, we study the interplay between the particle plasmon and electron hole pairs, which enables us to develop a quantitative model to fully describe the two and three photon luminescence emission of single gold nanoparticles.

physics.optics↗

arXiv2018

Understanding Weight Normalized Deep Neural Networks with Rectified Linear Units

This paper presents a general framework for norm-based capacity control for $L_{p,q}$ weight normalized deep neural networks. We establish the upper bound on the Rademacher complexities of this family. With an $L_{p,q}$ normalization where $q\le p^*$, and $1/p+1/p^{*}=1$, we discuss properties of a width-independent capacity control, which only depends on depth by a square root term. We further analyze the approximation properties of $L_{p,q}$ weight normalized deep neural networks. In particular, for an $L_{1,\infty}$ weight normalized network, the approximation error can be controlled by the $L_1$ norm of the output layer, and the corresponding generalization error only depends on the architecture by the square root of the depth.

cs.LG↗

arXiv2018

Describe and Attend to Track: Learning Natural Language guided Structural Representation and Visual Attention for Object Tracking

The tracking-by-detection framework requires a set of positive and negative training samples to learn robust tracking models for precise localization of target objects. However, existing tracking models mostly treat different samples independently while ignores the relationship information among them. In this paper, we propose a novel structure-aware deep neural network to overcome such limitations. In particular, we construct a graph to represent the pairwise relationships among training samples, and additionally take the natural language as the supervised information to learn both feature representations and classifiers robustly. To refine the states of the target and re-track the target when it is back to view from heavy occlusion and out of view, we elaborately design a novel subnetwork to learn the target-driven visual attentions from the guidance of both visual and natural language cues. Extensive experiments on five tracking benchmark datasets validated the effectiveness of our proposed method.

cs.CV↗

arXiv2018

Quality-Aware Multimodal Saliency Detection via Deep Reinforcement Learning

Incorporating various modes of information into the machine learning procedure is becoming a new trend. And data from various source can provide more information than single one no matter they are heterogeneous or homogeneous. Existing deep learning based algorithms usually directly concatenate features from each domain to represent the input data. Seldom of them take the quality of data into consideration which is a key issue in related multimodal problems. In this paper, we propose an efficient quality-aware deep neural network to model the weight of data from each domain using deep reinforcement learning (DRL). Specifically, we take the weighting of each domain as a decision-making problem and teach an agent learn to interact with the environment. The agent can tune the weight of each domain through discrete action selection and obtain a positive reward if the saliency results are improved. The target of the agent is to achieve maximum rewards after finished its sequential action selection. We validate the proposed algorithms on multimodal saliency detection in a coarse-to-fine way. The coarse saliency maps are generated from an encoder-decoder framework which is trained with content loss and adversarial loss. The final results can be obtained via adaptive weighting of maps from each domain. Experiments conducted on two kinds of salient object detection benchmarks validated the effectiveness of our proposed quality-aware deep neural network.

cs.CV↗

arXiv2018

Defensive Dropout for Hardening Deep Neural Networks under Adversarial Attacks

Deep neural networks (DNNs) are known vulnerable to adversarial attacks. That is, adversarial examples, obtained by adding delicately crafted distortions onto original legal inputs, can mislead a DNN to classify them as any target labels. This work provides a solution to hardening DNNs under adversarial attacks through defensive dropout. Besides using dropout during training for the best test accuracy, we propose to use dropout also at test time to achieve strong defense effects. We consider the problem of building robust DNNs as an attacker-defender two-player game, where the attacker and the defender know each others' strategies and try to optimize their own strategies towards an equilibrium. Based on the observations of the effect of test dropout rate on test accuracy and attack success rate, we propose a defensive dropout algorithm to determine an optimal test dropout rate given the neural network model and the attacker's strategy for generating adversarial examples.We also investigate the mechanism behind the outstanding defense effects achieved by the proposed defensive dropout. Comparing with stochastic activation pruning (SAP), another defense method through introducing randomness into the DNN model, we find that our defensive dropout achieves much larger variances of the gradients, which is the key for the improved defense effects (much lower attack success rate). For example, our defensive dropout can reduce the attack success rate from 100% to 13.89% under the currently strongest attack i.e., C&W attack on MNIST dataset.

cs.CR↗

arXiv2018

Billion-scale Network Embedding with Iterative Random Projection

Network embedding, which learns low-dimensional vector representation for nodes in the network, has attracted considerable research attention recently. However, the existing methods are incapable of handling billion-scale networks, because they are computationally expensive and, at the same time, difficult to be accelerated by distributed computing schemes. To address these problems, we propose RandNE (Iterative Random Projection Network Embedding), a novel and simple billion-scale network embedding method. Specifically, we propose a Gaussian random projection approach to map the network into a low-dimensional embedding space while preserving the high-order proximities between nodes. To reduce the time complexity, we design an iterative projection procedure to avoid the explicit calculation of the high-order proximities. Theoretical analysis shows that our method is extremely efficient, and friendly to distributed computing schemes without any communication cost in the calculation. We also design a dynamic updating procedure which can efficiently incorporate the dynamic changes of the networks without error aggregation. Extensive experimental results demonstrate the efficiency and efficacy of RandNE over state-of-the-art methods in several tasks including network reconstruction, link prediction and node classification on multiple datasets with different scales, ranging from thousands to billions of nodes and edges.

cs.SI↗

arXiv2018

On multiplying curves in the Kauffman bracket skein algebra of the thickened four-holed sphere

Based on the presentation of the Kauffman bracket skein module of the torus given by the third author in previous work, Charles D. Frohman and Răzvan Gelca established a complete description of the multiplicative operation leading to a famous product-to-sum formula. In this paper, we study the multiplicative structure of the Kauffman bracket skein algebra of the thickened four-holed sphere. We present an algorithm to compute the product of any two elements of the algebra, and give an explicit formula for some families of curves. We surmise that the algorithm has quasi-polynomial growth with respect to the number of crossings of a pair of curves. Further, we conjecture the existence of a positive basis for the algebra.

math.GT↗

arXiv2018

Isogeometric Least-squares Collocation Method with Consistency and Convergence Analysis

In this paper, we present the isogeometric least-squares collocation (IGA-L) method, which determines the numerical solution by making the approximate differential operator fit the real differential operator in a least-squares sense. The number of collocation points employed in IGA-L can be larger than that of the unknowns. Theoretical analysis and numerical examples presented in this paper show the superiority of IGA-L over state-of-the-art collocation methods. First, a small increase in the number of collocation points in IGA-L leads to a large improvement in the accuracy of its numerical solution. Second, IGA-L method is more flexible and more stable, because the number of collocation points in IGA-L is variable. Third, IGA-L is convergent in some cases of singular parameterization. Moreover, the consistency and convergence analysis are also developed in this paper.

math.NA↗

arXiv2018

Fokker-Planck equation driven by asymmetric Lévy motion

Non-Gaussian Lévy noises are present in many models for understanding underlining principles of physics, finance, biology and more. In this work, we consider the Fokker-Planck equation(FPE) due to one-dimensional asymmetric Lévy motion, which is a nonlocal partial differential equation. We present an accurate numerical quadrature for the singular integrals in the nonlocal FPE and develop a fast summation method to reduce the order of the complexity from $O(J^2)$ to $O(J\log J)$ in one time-step, where $J$ is the number of unknowns. We also provide conditions under which the numerical schemes satisfy maximum principle. Our numerical method is validated by comparing with exact solutions for special cases. We also discuss the properties of the probability density functions and the effects of various factors on the solutions, including the stability index, the skewness parameter, the drift term, the Gaussian and non-Gaussian noises and the domain size.

math.DS↗

arXiv2018

Tracking Multiple Moving Objects Using Unscented Kalman Filtering Techniques

It is an important task to reliably detect and track multiple moving objects for video surveillance and monitoring. However, when occlusion occurs in nonlinear motion scenarios, many existing methods often fail to continuously track multiple moving objects of interest. In this paper we propose an effective approach for detection and tracking of multiple moving objects with occlusion. Moving targets are initially detected using a simple yet efficient block matching technique, providing rough location information for multiple object tracking. More accurate location information is then estimated for each moving object by a nonlinear tracking algorithm. Considering the ambiguity caused by the occlusion among multiple moving objects, we apply an unscented Kalman filtering (UKF) technique for reliable object detection and tracking. Different from conventional Kalman filtering (KF), which cannot achieve the optimal estimation in nonlinear tracking scenarios, UKF can be used to track both linear and nonlinear motions due to the unscented transform. Further, it estimates the velocity information for each object to assist to the object detection algorithm, effectively delineating multiple moving objects of occlusion. The experimental results demonstrate that the proposed method can correctly detect and track multiple moving objects with nonlinear motion patterns and occlusions.

cs.CV↗

arXiv2018

Structural Deep Embedding for Hyper-Networks

Network embedding has recently attracted lots of attentions in data mining. Existing network embedding methods mainly focus on networks with pairwise relationships. In real world, however, the relationships among data points could go beyond pairwise, i.e., three or more objects are involved in each relationship represented by a hyperedge, thus forming hyper-networks. These hyper-networks pose great challenges to existing network embedding methods when the hyperedges are indecomposable, that is to say, any subset of nodes in a hyperedge cannot form another hyperedge. These indecomposable hyperedges are especially common in heterogeneous networks. In this paper, we propose a novel Deep Hyper-Network Embedding (DHNE) model to embed hyper-networks with indecomposable hyperedges. More specifically, we theoretically prove that any linear similarity metric in embedding space commonly used in existing methods cannot maintain the indecomposibility property in hyper-networks, and thus propose a new deep model to realize a non-linear tuplewise similarity function while preserving both local and global proximities in the formed embedding space. We conduct extensive experiments on four different types of hyper-networks, including a GPS network, an online social network, a drug network and a semantic network. The empirical results demonstrate that our method can significantly and consistently outperform the state-of-the-art algorithms.

cs.SI↗

arXiv2018

Semi-Supervised Convolutional Neural Networks for Human Activity Recognition

Labeled data used for training activity recognition classifiers are usually limited in terms of size and diversity. Thus, the learned model may not generalize well when used in real-world use cases. Semi-supervised learning augments labeled examples with unlabeled examples, often resulting in improved performance. However, the semi-supervised methods studied in the activity recognition literatures assume that feature engineering is already done. In this paper, we lift this assumption and present two semi-supervised methods based on convolutional neural networks (CNNs) to learn discriminative hidden features. Our semi-supervised CNNs learn from both labeled and unlabeled data while also performing feature learning on raw sensor data. In experiments on three real world datasets, we show that our CNNs outperform supervised methods and traditional semi-supervised learning methods by up to 18% in mean F1-score (Fm).

cs.LG↗

arXiv2017

Uniaxial and hydrostatic pressure effects in alpha-RuCl3 single crystals via thermal-expansion measurements

We present high-resolution thermal-expansion and specific-heat measurements of single crystalline alpha-RuCl3. An extremely hysteretic structural transition expanding over 100 K is observed by thermal- expansion along both crystallographic axes, which we attribute to a change of stacking sequence of the RuCl3 layers. Three magnetic transitions are observed, which we link to the different stacking sequences. Using our data and thermodynamic relations, we derive the uniaxial and hydrostatic pressure derivatives of all three magnetic transitions. Our results demonstrate that magnetic order should be totally suppressed by very moderate pressures of 0.3 GPa to 0.9 GPa. Finally, we discuss why our results differ from recent hydrostatic pressure measurements and suggest a possible route to reaching the spin-liquid state in alpha-RuCl3.

cond-mat.str-el↗

arXiv2017

TIMERS: Error-Bounded SVD Restart on Dynamic Networks

Singular Value Decomposition (SVD) is a popular approach in various network applications, such as link prediction and network parameter characterization. Incremental SVD approaches are proposed to process newly changed nodes and edges in dynamic networks. However, incremental SVD approaches suffer from serious error accumulation inevitably due to approximation on incremental updates. SVD restart is an effective approach to reset the aggregated error, but when to restart SVD for dynamic networks is not addressed in literature. In this paper, we propose TIMERS, Theoretically Instructed Maximum-Error-bounded Restart of SVD, a novel approach which optimally sets the restart time in order to reduce error accumulation in time. Specifically, we monitor the margin between reconstruction loss of incremental updates and the minimum loss in SVD model. To reduce the complexity of monitoring, we theoretically develop a lower bound of SVD minimum loss for dynamic networks and use the bound to replace the minimum loss in monitoring. By setting a maximum tolerated error as a threshold, we can trigger SVD restart automatically when the margin exceeds this threshold.We prove that the time complexity of our method is linear with respect to the number of local dynamic changes, and our method is general across different types of dynamic networks. We conduct extensive experiments on several synthetic and real dynamic networks. The experimental results demonstrate that our proposed method significantly outperforms the existing methods by reducing 27% to 42% in terms of the maximum error for dynamic network reconstruction when fixing the number of restarts. Our method reduces the number of restarts by 25% to 50% when fixing the maximum error tolerated.

cs.SI↗

arXiv2017

A Survey on Network Embedding

Network embedding assigns nodes in a network to low-dimensional representations and effectively preserves the network structure. Recently, a significant amount of progresses have been made toward this emerging network analysis paradigm. In this survey, we focus on categorizing and then reviewing the current development on network embedding methods, and point out its future research directions. We first summarize the motivation of network embedding. We discuss the classical graph embedding algorithms and their relationship with network embedding. Afterwards and primarily, we provide a comprehensive overview of a large number of network embedding methods in a systematic manner, covering the structure- and property-preserving network embedding methods, the network embedding methods with side information and the advanced information preserving network embedding methods. Moreover, several evaluation approaches for network embedding and some useful online resources, including the network data sets and softwares, are reviewed, too. Finally, we discuss the framework of exploiting these network embedding methods to build an effective system and point out some potential future directions.

cs.SI↗

arXiv2017

Angle Dependent Interlayer Magnetoresistance (ILMR) in Multilayer Graphene Stacks

Interlayer magnetoresistance (ILMR) effect is explored in a vertical stack of weakly coupled multilayer graphene as grown by chemical vapor deposition (CVD). This effect has been characterized as a function of temperature and tilt angle of the magnetic field with respect to the interlayer current. To our knowledge, this is the first experimental report on angle dependent ILMR effect in graphitic systems. Our data agrees qualitatively with the existing theories of ILMR in multilayer massless Dirac Fermion systems. However, a sharper change in ILMR has been observed as the tilt angle of the magnetic field is varied. A physical explanation of this effect is proposed, which is consistent with our experimental scenario.

cond-mat.mes-hall↗

arXiv2017

On the Statistical Efficiency of Compositional Nonparametric Prediction

In this paper, we propose a compositional nonparametric method in which a model is expressed as a labeled binary tree of $2k+1$ nodes, where each node is either a summation, a multiplication, or the application of one of the $q$ basis functions to one of the $p$ covariates. We show that in order to recover a labeled binary tree from a given dataset, the sufficient number of samples is $O(k\log(pq)+\log(k!))$, and the necessary number of samples is $Ω(k\log (pq)-\log(k!))$. We further propose a greedy algorithm for regression in order to validate our theoretical findings through synthetic experiments.

stat.ML↗