Search

Big data will cause the system for business public opinion to be overburdened, and dynamic changes in computing resources will cause tasks to be delayed. To end the situation, this study assigns non-fixed execution time to each task node based on the task soft deadline and task constraints and solves the problem of difficult task scheduling caused by task dependency constraints. Aiming at the problem of task delay caused by dynamic changes of computing resources, this paper proposes an adaptive offloading and scheduling algorithm for dependent tasks in the mobile edge computing environment. This study takes the economic efficiency analysis system as an example and uses the resource allocation management algorithm based on linked lists and edge servers to study the communication resource allocation management of the economic efficiency analysis system. In addition, this study designs experiments to perform performance analysis of the algorithm proposed by this study. The research results show that the proposed algorithm has an obvious effect. [ABSTRACT FROM AUTHOR]

This paper presents a constrained adaptive dynamic programming (CADP) algorithm to solve general nonlinear nonaffine optimal control problems with known dynamics. Unlike previous ADP algorithms, it can directly deal with problems with state constraints. Firstly, a constrained generalized policy iteration (CGPI) framework is developed to handle state constraints by transforming the traditional policy improvement process into a constrained policy optimization problem. Next, we propose an actor-critic variant of CGPI, called CADP, in which both policy and value functions are approximated by multi-layer neural networks to directly map the system states to control inputs and value function, respectively. CADP linearizes the constrained optimization problem locally into a quadratically constrained linear programming problem, and then obtains the optimal update of the policy network by solving its dual problem. A trust region constraint is added to prevent excessive policy update, thus ensuring linearization accuracy. We determine the feasibility of the policy optimization problem by calculating the minimum trust region boundary and update the policy using two recovery rules when infeasible. The vehicle control problem in the path-tracking task is used to demonstrate the effectiveness of this proposed method. [ABSTRACT FROM AUTHOR]

Minimizing energy consumption is a critical challenge for real-time workflows, particularly in heterogeneous cloud computing systems. State-of-the-art algorithms aim to minimize the energy consumed for processing such applications by choosing virtual machines (VMs) to shut down from all opened VMs (i.e., VM merging). However, such VM merging through an "on-to-close" approach usually incurs high computational complexity. This paper proposes an energy-efficient VM opening (EEVO) algorithm that is capable of choosing VMs to turn on from all closed VMs while satisfying the real-time constraint of applications. Considering that there are slacks that can be eliminated or reduced between adjacently scheduled tasks after using the EEVO algorithm, a dynamic scaling down EEVO algorithm (DEEVO) is further proposed. DEEVO is implemented by scaling down the frequency of VMs executing each task based on the dynamic voltage and frequency scaling (DVFS) technique. Experimental results demonstrate that, with the above-mentioned improvements, DEEVO achieves lower energy consumption for real-time workflows than state-of-the-art algorithms do. In addition, DEEVO outperforms state-of-the-art algorithms in the computational efficiency of accomplishing task scheduling. [ABSTRACT FROM AUTHOR]

Communication in parallel systems imposes significant overhead which often turns out to be a bottleneck in parallel machine learning. To relieve some of this overhead, in this paper, we present EventGraD - an algorithm with event-triggered communication for stochastic gradient descent in parallel machine learning. The main idea of this algorithm is to modify the requirement of communication at every iteration in standard implementations of stochastic gradient descent in parallel machine learning to communicating only when necessary at certain iterations. We provide theoretical analysis of convergence of our proposed algorithm. We also implement the proposed algorithm for data-parallel training of a popular residual neural network used for training the CIFAR-10 dataset and show that EventGraD can reduce the communication load by up to 60% while retaining the same level of accuracy. In addition, EventGraD can be combined with other approaches such as Top-K sparsification to decrease communication further while maintaining accuracy. [ABSTRACT FROM AUTHOR]

With the development of big data and artificial intelligence, distributed optimization has emerged as an indispensable tool for solving large-scale problems. In particular, the multi-agent system based on distributed information processing can be elaborately designed for distributed optimization, in which the agents collaboratively minimize a global objective function made up of a sum of local objective cost functions subject to some local and/or global constraints. Inspired by the applications involving resource allocation, machine learning, power systems, sensor networks and cloud computing, a variety of distributed optimization models and algorithms have been investigated and developed. The optimization models include unconstrained and constrained problems in continuous and discontinuous systems with undirected and directed communication topology graphs. The constraints include bounded constraint, separable and inseparable equality and inequality constraints. Meanwhile, in distributed algorithms, every agent executes its local computation and updating on basis of its own data information and that exchanging with its neighboring agents by means of the underlying communication networks, in order to deal with the optimization problems in a distributed way. This paper is designed to provide a comprehensive overview of extant distributed models and algorithms for distributed optimization. [ABSTRACT FROM AUTHOR]

[Display omitted] • A distributed algorithm is proposed for the generalized Nash equilibrium seeking. • The proposed algorithm is available for a more general Nash game. • The proposed algorithm can achieve an exponential convergence rate. In this paper, a distributed optimization algorithm is proposed for aggregative game with coupled constraints. Based on the singular perturbation system, the generalized Nash equilibrium is sought by a group of agents. By employing the average consensus method in the fast manifold, the aggregates in the object function can be estimated via simple information exchanges, as well as the aggregate of dual variables, which provides necessary information for the fully distributed algorithm design. Moreover, the exponential convergence of the proposed algorithm is explored based on the Lyapunov method, the properties of the variational inequality and the characteristic of the singular perturbation system. Application to the resource competition problem in smart grid verifies the effectiveness of the proposed algorithm. [ABSTRACT FROM AUTHOR]

This paper presents an adaptive grid-based clustering algorithm called as "AGFC", which uses a forest-like query structure to sequentially discovers multiple arbitrary-shaped clusters from the grid. The main advantage of AGFC is that it can effectively generate a reasonable grid division with a simple startup parameter. This method determines the appropriate grid division width through the minimum gap between the peaks and valleys of the density curve in a specific dimension, which depends on the distribution of the sample, to overcome the subjectivity of manual determination to a certain extent. Furthermore, in the forest-like query structure, it constructs a "Aggregation Judgment" criterion for high-density cells to find out the possible clusters through the merging of cells. Finally, using the "Re-clustering process" to eliminate very small clusters and further repairing the edge areas of the main clusters. The experimental results show that the proposed method can obtain competitive results under the premise of automatically determining the grid. [ABSTRACT FROM AUTHOR]

[Display omitted] • Multidimensional data can be voxelized to obtain a simpler representation. • A simple likelihood function can be used in place of the Euclidean distance. • Classification can be done via partitioning the data into Voronoi regions. • Comparable inference performance with the SVM family of algorithms is achieved. Voronoi tessellations are used to partition the Euclidean space into polyhedral regions, which are called Voronoi cells. Labeling the Voronoi cells with the class information, we can map any classification problem into a Voronoi tessellation. In this way, the classification problem changes into a query of just finding the enclosing Voronoi cell. In order to accomplish this task, we have developed a new algorithm which generates a labeled Voronoi tessellation that partitions the training data into polyhedral regions and obtains interclass boundaries as an indirect result. It is called Supervised k-Voxels or in short Super-k. We are introducing Super-k as a foundational new algorithm and opening the possibility of a new family of algorithms. In this paper, it is shown via comparisons on certain datasets that the Super-k algorithm has the potential of providing comparable performance of the well-known SVM family of algorithms. [ABSTRACT FROM AUTHOR]

The prediction of short term power load owns a great influence on performance of the whole electric system. Raising the result of power load forecasting is always a research spot. This paper proposes a method combined Elman neural network (ENN) and the particle swarm optimization (PSO) for the short-term power load forecasting. Firstly, this paper introduces the principle of ENN and PSO algorithm respectively and analyzes performance of network influenced by parameters of ENN. Then the particle swarm optimization algorithm is applied to searching the optimal learning rate of ENN. To study the capability of the method proposed in this paper, the method is utilized for the short-term power load forecasting, which is suitable to be solved by ENN. Besides, a comparison experiment on this method (PSO–ENN) with general regression neural network (GRNN), the original ENN and the traditional back-propagation neural network (BPNN) is given out to illustrate effectiveness of PSO–ENN. [ABSTRACT FROM AUTHOR]

In this paper, a novel control scheme is developed to solve an optimal containment control problem of unknown continuous-time multi-agent systems. Different from traditional adaptive dynamic programming (ADP) algorithms, this paper proposes an internal reinforcement ADP algorithm (IR-ADP), in which the internal reinforcement signals are added in order to facilitate the learning process. Then a distributed containment control law is designed for each agent with the internal reinforcement signal. The convergence of this IR-ADP algorithm and the stability of the closed-loop multi-agent system are analyzed theoretically. For the implementation of the optimal controllers, three neural networks (NNs), namely internal reinforcement NNs, critic NNs and actor NNs, are utilized to approximate the internal reinforcement signals, the performance indices and optimal control laws, respectively. Finally, some simulation results are provided to demonstrate the effectiveness of the proposed algorithm. [ABSTRACT FROM AUTHOR]

Deep learning technologies have been rapidly developing recently. They have shown excellent performances in many fields. However, deep learning networks have weak adaptability to small sample sizes.Usually, deep learning networks require tens of thousands of samples to avoid overfitting. In contrast, the kernel method can deal with small sample sizes. In this paper, we use only dozens of samples to train a successful classifier. Deep multiple kernel learning (DMKL) has emerged in recent years. It combines the ideas of deep learning and multiple kernel learning. Unfortunately, the DMKL network with a fixed structure cannot adapt to data of different dimensions and sizes. Therefore, in this paper, we propose a novel depth-width-scaling multiple kernel learning (DWS-MKL) algorithm. It has the ability to adjust the architecture according to the input data. We optimize the estimation of leave-one-out error by using the span bound instead of the dual objective function. Finally, we choose a large number of data sets from the UCI benchmark data sets for classification tasks. We also evaluate DWS-MKL on the MNIST data set. The experimental results show that different frameworks have different performances on the same dataset. Our DWS-MKL algorithm obtains better classification results than the state-of-the-art kernel learning algorithms, as determined by a thorough comparison. The encouraging results demonstrate that our method has the potential to improve generalization performance of the model. [ABSTRACT FROM AUTHOR]

This paper investigates the fully complex mini-batch gradient algorithm for training complex-valued neural networks. Mini-batch gradient method has been widely used in neural network training, however, its convergence analysis is usually restricted to real-valued neural networks and of probability nature. By introducing a new Taylor mean value theorem for analytic functions, in this paper we establish deterministic convergence results for the fully complex mini-batch gradient algorithm under mild conditions. The deterministic convergence here means that the algorithm will deterministically converge, and both the weak convergence and strong convergence will be proved. Benefited from the newly introduced mean value theorem, our results are of global nature in that they are valid for arbitrarily given initial values of the weights. The theoretical findings are validated with a simulation example. [ABSTRACT FROM AUTHOR]

In this paper, we study the decentralized AdaBoost problem over sensor networks, and propose a fully decentralized AdaBoost algorithm, where each sensor can obtain the centralized global solution without transmission of private dataset. By decomposing the centralized cost function into a summation of local ones, we convert decentralized AdaBoost problem into a distributed optimization problem, and design a distributed alternating minimization method to solve it. In order to improve convergence rate, motivated by Nesterov gradient descent method, we propose a fast decentralized AdaBoost algorithm. Then, we prove the convergence of proposed algorithms. Moreover, we deduce decentralized AdaBoost algorithm for logistic regression in detail. The simulations with Spam-Email dataset illustrate the effectiveness of proposed algorithms. [ABSTRACT FROM AUTHOR]

In this paper, a new approach is proposed for the smooth path planning of mobile robot based on a new quartic Bezier transition curve and an improved particle swarm optimization (PSO) algorithm. First, a dedicatedly constructed quartic Bezier transition curve with three overlapped control points is developed to fulfil the G 3 -continuity of the smooth path at the joints of the path segments, so as to guarantee the high-order smoothness of the path for the movement of mobile robot. Then, the smooth path planning of mobile robot is formulated mathematically as an optimization problem under several criteria and constraints of the smooth path, e.g. length, smoothness, safety and robot kinematics. Furthermore, an improved PSO with adaptive weighted delay velocity (PSO-AWDV) algorithm is presented for the optimization problem of smooth path planning, where the parameter relationship to ensure the convergence of PSO-AWDV is derived through the stability analysis of the algorithm. Finally, several simulation experiments are carried out to confirm the effectiveness and superiority of the proposed new approach combined with the new quartic Bezier transition curve and the improved PSO-AWDV algorithm. [ABSTRACT FROM AUTHOR]

Early diagnosis of Autism Spectrum Disorder (ASD) plays a crucial role in the intervention of ASD. Traditionally, an ASD child needs to be diagnosed by a psychiatrist in the hospital, which is expensive, time-consuming, and influenced by expertise. In this paper, we present an objective, convenient, and effective method for classifying ASD children from raw video sequences by integrating the appearance-based features from facial expressions, head pose, and head trajectory. To better extract facial expression features, we propose a novel attention-based facial expression recognition algorithm to focus on key face areas like eyebrows, mouth, etc. Moreover, we use accumulative histogram to individually extract temporal and spatial information from facial expression, head pose and head trajectory of the video sequence. After fusing these three kinds of features, we feed them to Long Short-Term Memory (LSTM) and achieve a classification accuracy of 96.7% on our self-collected ASD video dataset. [ABSTRACT FROM AUTHOR]

Recently, the Extreme Learning Machine (ELM) algorithm has been applied to various fields due to its rapidity and significant generalization performance. Traditionally, deep learning (DL) and wavelet neural networks (WNN) methods reach a high classification accuracy in machine learning applications. As a result, a new structure based on WNN, deep architecture and ELM is proposed in this paper. The proposed method is based on Extreme Learning Machine Auto-Encoder with DL structure and a composite wavelet activation function used in the hidden nodes. To evaluate the performance of our approach, we used standard benchmark data-sets, namely COIL-20, Pima Indian Diabetes (PID), MNIST and EMNIST. Experimental results show that our method offers satisfactory results and performance compared to other approaches. [ABSTRACT FROM AUTHOR]

This paper proposes a new information-based distributed extended Kalman filter algorithm under dynamic quantization. Our quantization framework has the advantage of utilizing online updated quantizer's parameters. A practical adjustment strategy is derived to ensure the availability of adaptive quantizer's parameters for the encoder and decoder. It is proved that estimation error of the proposed algorithm is exponentially bounded in mean square under some assumptions. A numerical example concerning target tracking is presented to demonstrate the validity of the main results, in which a complex network model is used to simulate the sensor network. [ABSTRACT FROM AUTHOR]

Gradient-based algorithms are commonly used for training radial basis function neural network (RBFNN). However, it is still difficult to avoid vanishing gradient to improve the learning performance in the training process. For this reason, in this paper, an accelerated second-order learning (ASOL) algorithm is developed to train RBFNN. First, an adaptive expansion and pruning mechanism (AEPM) of gradient space, based on the integrity and orthogonality of hidden neurons, is designed. Then, the effective gradient information is constantly added to gradient space and the redundant gradient information is eliminated from gradient space. Second, with AEPM, the neurons are generated or pruned accordingly. In this way, a self-organizing RBFNN (SORBFNN) which reduces the structure complexity and improves the generalization ability is obtained. Then, the structure and parameters in the learning process can be optimized by the proposed ASOL-based SORBFNN (ASOL-SORBFNN). Third, some theoretical analyses including the efficiency of the proposed AEPM on avoiding the vanishing gradient and the stability of SORBFNN in the process of structural adjustment are given, then the successful application of the proposed ASOL-SORBFNN is guaranteed. Finally, to illustrate the advantages of the proposed ASOL-SORBFNN, several experimental studies are examined. By comparing with other existing approaches, the results show that ASOL-SORBFNN performs well in terms of both learning speed and prediction accuracy. [ABSTRACT FROM AUTHOR]

Considering the fact that it is very difficult to fully model an autonomous underwater vehicle (AUV) in the complex water environment, this paper presents a model-free tracking control strategy for an AUV in the presence of unknown disturbances. We first formulate an optimized control problem by defining a tracking Hamilton–Jacobi–Isaac (HJI) equation. Then, we present a reinforcement learning (RL) algorithm to compute an optimized solution by learning from the HJI equation online. It is noted that during the learning period, no information about the AUV's dynamics is needed. In order to demonstrate the efficiency of the proposed strategy, numerical simulation is considered, results are validated and discussed. [ABSTRACT FROM AUTHOR]

This paper investigates the consensus of a multiagent system (MAS) under binary-valued communication with directed topology. An improved two-time-scale algorithm that alternates between control and estimation is proposed. Compared with the existing two-time-scale algorithm for the undirected topology case, we relax the conditions on the algorithm parameters, thereby providing more choices for practical implementations. The asymptotic property of the algorithm is analyzed by analyzing the convergence of the explicit closed-loop solution. To reduce the effect of binary communication on the consensus value for a single-sample path, the selection method for obtaining suitable parameters is given. To demonstrate their effectiveness, the selection method and algorithm are applied to the reputation management of a public welfare platform. [ABSTRACT FROM AUTHOR]

The issue of stability and group output consensus is investigated for the discrete-time heterogeneous networked multi-agent systems with communication constraints(e.g., time delays and data loss) in this paper. Firstly, the couple-group output consensus is analyzed theoretically, the communication constraints are compensated by the prediction method. Secondly, the necessary and sufficient condition is given to ensure the stability of the system, achieve the couple-group consensus with reference input control, and relax the topology constraint of in-degrees balance by cooperative-competitive interactions. Furthermore, the result of couple-group consensus is extended to multi-group consensus based on a novel predictive control algorithm. Finally, a numerical simulation shows that the proposed networked predictive control method can effectively overcome the communication constraints, the dynamic performance and control effect are similar to the traditional control without communication constraints. [ABSTRACT FROM AUTHOR]

This paper studies the differential privacy-preserving problem for multi-agent systems (MASs) in the presence of antagonistic information over signed digraph. As for the structurally balanced case, an ε -differential privacy algorithm is proposed, upon which some sufficient conditions guaranteeing almost sure bipartite consensus are given. Based on the above scheme, the tradeoff between the system performance and the privacy guarantee is elaborated, and the optimal noise is also devised. Moreover, the proposed privacy preserving scheme is further applied to the scenario of structurally unbalanced graph, where a criterion with respect to almost sure stability of the considered system is derived, as well as the privacy preserving condition. This extends the balanced interaction scenario, and consequently the cooperative multi-agent systems. Finally, numerical simulations are presented to demonstrate the effectiveness of our results. [ABSTRACT FROM AUTHOR]

Multinomial logistic regression (MLR) is a useful tool for solving multi-classification problems. The l q , 0 (q ⩾ 1) norm is an ideal regularization term for characterizing group sparsity in multinomial logistic regression and selecting important features in the high dimensional data. However, l q , 0 regularized multinomial logistic regression ( l q , 0 -MLR) is nonconvex, discontinuous, and NP-hard. Thus, most prior studies adopted a continuous approximation of the l q , 0 norm. In this paper, we present a novel l q , 0 -proximal Newton algorithm ( l q , 0 -PNA) to solve the l q , 0 -MLR. We first define a strong α -stationary point and prove that this point is a local minimizer of l q , 0 -MLR. We then convert such a point into a stationary equation and solve it by l q , 0 -PNA, which is a Newton-type method running on a group sparse subspace with a low computational cost. Furthermore, we establish a locally quadratic convergence of l q , 0 -PNA. Finally, numerical experiments on simulated and real data show the superiority of l q , 0 -PNA in terms of computational time and accuracy, when compared with six state-of-the-art solvers, especially for high dimensional data. [ABSTRACT FROM AUTHOR]

As one of the core technologies of the automatic control system for unmanned surface vehicles (USVs), autonomous collision avoidance algorithm is the key to ensure the safe navigation of USVs. In this paper, path planning and dynamic collision avoidance (PPDC) algorithm which obeys COLREGs is proposed for USVs. In order to avoid unnecessary collision avoidance actions, the risk assessment model is developed, which is used to determine the switching time of path planning and dynamic collision avoidance. In order to train the algorithm which complies with the COLREGs, the encounter situation is divided quantitatively, which is regarded as the input state of the system, so that the high-dimensional input is successfully avoided. The state space of the USV is defined by relative parameters to improve the generalization ability of the algorithm, meanwhile, a network structure based on DDPG is designed to achieve the continuous output of thrust and rudder angle. Combined with path planning, collision avoidance, compliance with COLREGs and smooth arrival task, four kinds of reward functions are designed. In order to solve the problem of low training efficiency of experience replay mechanism in DDPG, cumulative priority sampling mechanism is proposed. Through the simulation and verification in a variety of scenarios, it is proved that PPDC algorithm has the function of path planning and dynamic collision avoidance in compliance with COLREGs, which has good real-time performance and security. [ABSTRACT FROM AUTHOR]

Tensor data analysis is the evolutionary step of data analysis to more than two dimensions. Dealing with tensor data is often based on tensor decomposition methods. The present paper focuses on unsupervised learning and provides a python package referred to as TensorClus including novel co-clustering algorithms of three-way data. All proposed algorithms are based on the latent block models and suitable to different types of data, sparse or not. They are successfully evaluated on challenges in text mining, recommender systems, and hyperspectral image clustering. TensorClus is an open-source Python package that allows easy interaction with other python packages such as NumPy and TensorFlow; it also offers an interface with some tensor decomposition packages namely Tensorly and TensorD on the one hand, and on the other, the co-clustering package Coclust. Finally, it provides CPU and GPU compatibility. The TensorClus library is available at https://pypi.org/project/TensorClus/. [ABSTRACT FROM AUTHOR]

[Display omitted] • A novel polar representation is introduced for video object segmentation. • An asymmetric Siamese network is developed using similar backbones with different depths. • We design the repeated cross correlation and semi-FPN based on peeling convolutions. Video object segmentation (VOS) is an essential part of autonomous vehicle navigation. Besides the accuracy metric, the real-time speed is very important for the algorithms of autonomous vehicles. In this paper, we propose a semi-supervised real-time method based on the Siamese network using a new polar representation. The input of bounding boxes are initialized rather than the object masks, which are applied to the video object detection tasks. The polar representation could reduce the parameters for encoding masks with subtle accuracy loss, so that the algorithm speed can be improved significantly. An asymmetric siamese network is also developed to extract the features from different spatial scales. Moreover, the peeling convolution is proposed to reduce the antagonism among the branches of the polar head. The repeated cross-correlation and semi-FPN are designed based on this idea. The experimental results on the DAVIS-2016 dataset and other public datasets demonstrate the effectiveness of the proposed method. [ABSTRACT FROM AUTHOR]

The technology for Visual Odometry (VO) that estimates the position and orientation of the moving object through analyzing the image sequences captured by on-board cameras, has been well investigated with the rising interest in autonomous driving. This paper studies monocular VO from the perspective of Deep Learning (DL). Unlike most current learning-based methods, our approach, called DeepAVO, is established on the intuition that features contribute discriminately to different motion patterns. Specifically, we present a novel four-branch network to learn the rotation and translation by leveraging Convolutional Neural Networks (CNNs) to focus on different quadrants of optical flow input. To enhance the ability of feature selection, we further introduce an effective channel-spatial attention mechanism to force each branch to explicitly distill related information for specific Frame to Frame (F2F) motion estimation. Experiments on various datasets involving outdoor driving and indoor walking scenarios show that the proposed DeepAVO outperforms the state-of-the-art monocular methods by a large margin, demonstrating competitive performance to the stereo VO algorithm and verifying promising potential for generalization. [ABSTRACT FROM AUTHOR]

Dynamic area coverage algorithm is often used in multiple unmanned aerial vehicle (multi-UAV) systems to realize searching or monitoring an area of interest (AOI). Improving coverage efficiency is one of the important research issues of dynamic area coverage. In this paper, we propose a distributed dynamic area coverage algorithm based on a reinforcement learning (RL) algorithm to enhance the coverage efficiency in complex application environments. A coverage information fusion based discrete soft actor–critic algorithm (herein FDSAC) is proposed to solve the non-stationary problem of RL algorithm in area coverage task under the communication constraint environment. Considering the equivalence of UAVs in the area coverage tasks, we introduce a multi-UAV cooperative learning method for FDSAC by sharing the strategy and experience of the UAVs to accelerate the learning speed of FDSAC in multi-UAV system. With the FDSAC algorithm, the UAVs can intelligently select the best coverage points and achieve almost optimal coverage point planning for the entire coverage process. In addition, we also provide a coverage point adjustment method based on the distribution of obstacles to enable the proposed algorithm adapt to obstacle environments. The experimental results demonstrate that the proposed algorithm can efficiently complete the area coverage task in complex communication and stochastic control noise environment. The good scalability, environment adaptability, and practicality of our algorithm have been also confirmed in different complex environments of different experimental platforms. [ABSTRACT FROM AUTHOR]

The multi-robot task allocation problem has garnered significant attention in research and development. This paper addresses the multi-robot task allocation problem by introducing a unified model that seamlessly transforms into four popular mathematical models through simple parameter adjustments. We propose an efficient indicator-based multi-objective evolutionary algorithm with a hybrid encoding scheme for task execution order and robot starting point information. The algorithm employs the hypervolume indicator for environmental selection to enhance convergence and the modified crowding distance for archive updates to promote diversity. Additionally, an adaptive archive update mechanism is designed for time efficiency. In experiments comparing our proposed algorithm with 8 state-of-the-art algorithms on 18 randomly generated instances of various sizes, along with 4 real-world problems from the TSPLIB benchmark, our algorithm consistently outperformed the comparison algorithms in five key indicators. These results underscore the effectiveness of our approach in addressing real-world multi-robot task allocation problems. [ABSTRACT FROM AUTHOR]

In the last decade it became increasingly apparent the inability of technical metrics such as accuracy, sustainability, and non-regressiveness to well characterize the behavior of intelligent systems. In fact, they are nowadays requested to meet also ethical requirements such as explainability, fairness, robustness, and privacy increasing our trust in their use in the wild. Of course often technical and ethical metrics are in tension between each other but the final goal is to be able to develop a new generation of more responsible and trustworthy machine learning. In this paper, we focus our attention on machine learning algorithms and associated predictive models, questioning for the first time, from a theoretical perspective, if it is possible to simultaneously guarantee their performance in terms of both technical and ethical metrics towards machine learning algorithms that we can trust. In particular, we will investigate for the first time both theory and practice of deterministic and randomized algorithms and associated predictive models showing the advantages and disadvantages of the different approaches. For this purpose we will leverage the most recent advances coming from the statistical learning theory: Complexity-Based Methods, Distribution Stability, PAC-Bayes, and Differential Privacy. Results will show that it is possible to develop consistent algorithms which generate predictive models with guarantees on multiple trustworthiness metrics. • AI is nowadays requested to optimize both technical and ethical metrics. • Focus on ML algorithms and associated models (both deterministic and randomized). • We prove that it is possible to develop consistent algorithms and models. • We bound generalization in terms of both technical and ethical metrics. • We leverage the most recent advances coming from the statistical learning theory. [ABSTRACT FROM AUTHOR]

The target net method has been the foundation of deep reinforcement learning since Deepmind first proposed it in 2015. Almost all the current popular reinforcement learning algorithms include target net. However, while the slowly updated target network improves the stability of the algorithm, it also reduces the performance of the algorithm. In this paper, the authors design a novel triple-network algorithm(TPN). TPN combines the temporal-difference(TD) algorithm and policy gradient(PG) theorem. Using three networks to estimate the state value(v), action value (q) , and policy(π). These networks have no primary or secondary distinction but are trained synchronously and influence each other. The author found that through this TPN architecture, the convergence and stability of the algorithm can be greatly improved without increasing the amount of calculation. Although it is only a basic framework at present. The calculation process of TPN is simple and easy to implement. Experiments prove that the convergence speed and stability of TPN in discrete cases are better than PPO. • Proposed a new deep reinforcement learning algorithm that does not rely on target networks. • Presented the complete derivation process of the TPN algorithm. • Verified the effectiveness of proposed algorithm through experiments. [ABSTRACT FROM AUTHOR]

Most traditional multi-view spectral clustering algorithms involve two separate steps: solving the spectral embedding matrix and clustering, which may introduce errors during the clustering process. Moreover, in practical applications, the number of available views may increase over time, and the approach of re-fusing all views in each computation would result in elevated computational costs. In this paper, we propose a novel model: One-step Incremental Multi-view Spectral Clustering based on Graph Linkage learning (OIMvSC). OIMvSC only needs to store the consensus spectral embedding matrix and the consensus label matrix of all previous views and combines them with the spectral embedding matrix of the newly available view to solve the fused consensus spectral embedding matrix and consensus label matrix. To further enhance clustering performance, OIMvSC introduces graph linkage learning, which reduces erroneous connections between clusters while preserving correct connections within clusters. A convergent iterative algorithm for solving OIMvSC is proposed. Experimental results demonstrate that OIMvSC exhibits excellent clustering performance. [ABSTRACT FROM AUTHOR]

In the research of complex networks, how to find a set of nodes in the network with the most extensive range in the propagation process, i.e., the Influence Maximization (IM) problem, is one of the focal topics. Existing studies mainly consider the information dissemination process on networks and how to select diffusive nodes efficiently, but little attention has been paid to changes related to the network structure. In reality, networked systems are exposed to uncertain interferences and even destructive sabotages, and cascading failures are one common destruction that can cause networks to collapse even if only a small number of nodes fail. In the case of various complex environmental factors, how to select robust and influential nodes, i.e., the robust influence maximization (RIM) problem, is of great importance in promoting the realistic application of the influence maximization problem. This paper investigates the RIM problem under cascading failures to address the shortcomings in previous studies. Based on existing research, a new performance evaluation metric, R S-cf , is designed to assess the level of robust influence in a numerical form. For solving the seed determination problem, a Memetic algorithm towards the RIM problem under cascading failures, MA-RIM CF , is designed to find nodes with stable information propagation capability guided by R S-cf. Experiments have been conducted on both synthetic and realistic networks to validate the performance of the algorithm. Results indicate that MA-RIM CF can obtain competitive candidates over existing approaches, and seeds with robust and influential abilities are generated to solve diffusion dilemmas. [ABSTRACT FROM AUTHOR]

Matrix completion is extensively studied due to its wide applications in science and technology. In this paper, we concentrate our study on the matrix completion problem for image analysis tasks due to their immense importance and pervasive use in many fields. A rich collection of models has been proposed to capture both linear and nonlinear relationships latent in a matrix. Even though nonlinear models possess more powerful matrix completion capabilities than their linear counterparts, these models generally carry higher model complexity and tuning difficulties. To take advantage of the superior discriminative power offered by nonlinear models while curbing its deployment overheads, this paper proposes a novel nonlinear matrix completion model utilizing a deep learning-based approach. In contrast to existing nonlinear models, the new model carefully explores and exploits spatial locality among adjacent matrix elements exhibited in patches of various sizes and locations in a target matrix. Building upon this idea, a new patch-based nonlinear matrix completion algorithm is designed. The algorithm leverages a convolutional neural network to learn the predictive relationship between a matrix element and its surrounding elements through an end-to-end trainable fashion, leading to a capable and easy-to-deploy nonlinear matrix completion solution. To identify an optimal patch size suited for tackling a given matrix completion task without exhaustively enumerating all candidate patch sizes, the new algorithm is coupled with a fast stochastic search procedure, yielding a good trade-off between computational efficiency and accuracy. Extensive experiments are conducted to validate the effectiveness and advantages of the proposed algorithm for nonlinear matrix completion problem in comparison with a series of state-of-the-art algorithms. Experimental results consistently demonstrate the superiority of the new algorithm in completing images with a variety of random and textual noises. [ABSTRACT FROM AUTHOR]

In this paper, we study an important recommendation problem of exploiting users' one-class positive feedback such as "likes", which is usually termed as one-class collaborative filtering (OCCF). For modeling users' preferences beneath the observed one-class positive feedback, the similarity between two users is a key concept of constructing a neighborhood structure with like-minded users. With a well-constructed neighborhood, we can make a prediction of a user's preference to an un-interacted item by aggregating his or her neighboring users' tastes. However, the neighborhood constructed by a typical traditional method is usually asymmetric, meaning that a certain user may belong to the neighborhood of another user but the inverse is not necessarily true. Such an asymmetric structure may result in a less strong neighborhood, which is our major finding in this paper. As a response, we exploit the reciprocal neighborhood among users in order to construct a better neighborhood structure with more high-value users, which is expected to be less influenced by the active users. We then design a corresponding recommendation algorithm called k -reciprocal nearest neighbors algorithm (k -RNN). Extensive empirical studies on two large and public datasets show that our k -RNN performs significantly better than a closely related algorithm with the traditional asymmetric neighborhood and some competitive model-based recommendation methods. [ABSTRACT FROM AUTHOR]

In this paper, we investigate quantized synchronization control problem of memristive neural networks (MNNs) with time-varying delays via super-twisting algorithm. A feedback controller is introduced with quantized method. To enormously reduce the computational complexity of the controller under super-twisting algorithm, two quantized control schemes are proposed with uniform quantizer and logarithmic quantization. We obtain some sufficient conditions of specific control plans to guarantee that the driving MNNs can synchronize with the response MNNs. A neoteric Lyapunov functional is designed to analyze the synchronization problem. Finally, in this paper ending, some illustrative examples are given in support of our results. [ABSTRACT FROM AUTHOR]

• We propose a novel matrix inversion free algorithm for solving the Bayesian linear regression problem with Gaussian priors. • Compared with the conventional gradient based and EM algorithms, our proposed one runs significantly faster while achieving the similar precision performance. • An iterative method from a perspective of latent matrices is proposed for optimal search without breaking the symmetric positive definite manifold constraint. The Bayesian linear regression is a useful tool for many scientific communities. This paper presents a novel algorithm for solving the Bayesian linear regression problem with Gaussian priors, which shares the same spirit as the gradient based methods. In addition, the standard scheme for this task, the Expectation Maximization (EM) algorithm, involves matrix inversions but our proposed algorithm is free of. Numerical experiments demonstrate that the proposed algorithm performs as well as the gradient based and EM algorithms in term of precision, but runs significantly faster than the gradient based and EM algorithms. Due to its matrix-inversion-free nature, the algorithm of this paper is a viable alternative to the competing methods available in the literature. [ABSTRACT FROM AUTHOR]

• Proposed the infimal convolution smoothing technique to approximate the non-differentiable loss function. • Introduced a relaxation factor to transform the non-differentiable loss function into a smooth counterpart. • Provided convergence analysis for the algorithm under the APG and mAPG framework. • Evaluated the effectiveness of the proposed algorithm via numerical experiments. This paper addresses the robust sparse recovery problem in the presence of impulsive measurement noise. In order to overcome the poor performance of ℓ 2 -norm loss function with the outliers under the impulsive noise, we employ the ℓ 1 -norm as the loss function for the residual error, which is less sensitive to outliers in the measurements than the popular ℓ 2 -loss. To rise to the challenges introduced by the non-smooth problem, we first employ two smoothing strategies to approximate the ℓ 1 -norm loss function: one introduces a relaxation factor in the ℓ 1 -norm and the other uses the infimal convolution smoothing technique to transform it into a smooth counterpart. Both of them can approximate the ℓ 1 -norm with arbitrary degree of accuracy and provide a Lipschitz continuous gradient loss function. Then, we employ the accelerated proximal gradient (APG) and monotone APG (mAPG) frameworks for the convex and non-convex regularization functions, respectively. The convergence performance is discussed for generalized regularization penalty. The simulation result demonstrates our conclusions and indicates that the algorithm proposed in this paper can improve the reconstruction quality. [ABSTRACT FROM AUTHOR]

In this paper, a novel learnable population filter is proposed to solve the dynamic multi-objective problems (DMOPs), whose main idea is to pick out potential valuable individuals in the changing situation via the trained filter to facilitate the population convergence in a new environment. In particular, by selecting training samples from three different optional pools, rich information in the previous searching experiences can be sufficiently used to cope with the dynamic behaviors in DMOPs, thereby handling the imperfect history data availability caused by the environmental uncertainty to some extents. Then, the screened population in the new environment, which is regarded to have reliable quality that benefits accelerating the evolution, is used to initialize the static optimizer. In addition, partial random solutions are employed as supplement to the initial population to further enhance the diversity. It is shown from the benchmark evaluations that the proposed method outperforms some other popular algorithms on both convergence and diversity by seamlessly combining the mainstream strategies in dealing with the dynamic behaviors, which is a competitive method that conforms to the novel evolutionary transfer optimization (ETO) trend. Moreover, effectiveness of the core components is validated through extensive ablation studies, which brings a new sight in developing the learnable DMOP solvers. [ABSTRACT FROM AUTHOR]

In this paper, a distributed economic dispatch algorithm based on event-triggered and fixed-time consensus is proposed for optimal dispatching among generators in smart grid. Aiming to quickly achieve economic dispatch in distributed smart grid and significantly reduce the frequency of communication between generators, the algorithm can address the supply–demand balance between the generation side and the consumption side, as well as the capacity constraints of the generators. Different from the relevant work, the proposed incremental cost can converge in fixed-time and the settling time is independent of the initial state of the generators. It will provide more flexibility for the system. Meanwhile, a fully distributed event-triggered strategy is adopted, which can reduce the interactive information between generators and avoid the waste of communication resources. Furthermore, the proposed algorithm is robust to the time-varying communication network topology. Finally, several examples are presented that validate the effectiveness of the algorithm. [ABSTRACT FROM AUTHOR]

This paper proposes a text removal model, Text Remove Network (TRNet), which achieves an unprecedented clearing effect of picture text. The network uses a jump-connected U-net structure to encode and decode the generator, so as to obtain clearer and sharper texture details of the original image. To solve the problem of color distortion, the generator removes the batch normalization layer and uses ELUs as the activation layer of all convolutional layers. Through the comprehensive loss, which include reconstruction, content, style, total variation, and structural similarity (SSIM) loss, we can clear the image text and preserve the image information of the background, which solves the problem of incomplete text removal and loss of background texture. The local discriminator is used to evaluate the local consistency of the text erasure area. In a text elimination experiment on a synthetic dataset and the ICDAR 2013 dataset, this method had a good effect on foreground text erasure and background authenticity restoration. Experiments on a comprehensive dataset of real documents also showed good results. To achieve targeted removal of sensitive text information on pictures, we collected datasets based on real and synthetic documents, and experimental results were satisfactory. Compared to current and classic algorithms, our text removal algorithm performs best in Image Quality Assessment (IQA). [ABSTRACT FROM AUTHOR]

• An improved algorithm is introduced. • The unbounded position and nonconvex velocity constraints are considered. • The dynamics of all agents are assumed to be heterogeneneous. The distributed discrete-time heterogeneous multi-agent optimization problem with unbounded position constraints and nonconvex velocity constraints was considered in this paper, where the models of agents are described by first- or second- order difference equations, the position constraints are assumed to be unbounded and convex and the velocity constraints are assumed to be bounded, closed and nonconvex. An improved distributed algorithm is adopted, under which, all agents could collaboratively minimize the entire objective function and the positions and velocities could always stay at the corresponding constraint sets. Then the convergence analysis is completed by the coordination transformation and the properties of projection operator and constraint operator. Finally, we give examples to illustrate the correctness of results. [ABSTRACT FROM AUTHOR]

• To improve generalization performance, three novel PAC-Bayes meta-learning bounds are proposed. • Based on the ERM method, a PAC-Bayes meta-learning bound with a data-dependent prior is developed. • Its computational complexity is analyzed and experiments illustrates its effectiveness. Meta-learning aims to leverage experience from previous tasks to achieve an effective and fast adaptation ability when encountering new tasks. However, it is unclear how the generalization property applies to new tasks. Probably approximately correct (PAC) Bayes bound theory provides a theoretical framework to analyze the generalization performance for meta-learning with an explicit numerical generalization error upper bound. A tighter upper bound may achieve better generalization performance. However, for the PAC-Bayes meta-learning bound, the prior distribution is selected randomly which results in poor generalization performance. In this paper, we derive three novel generalization error upper bounds for meta-learning based on the PAC-Bayes relative entropy bound. Furthermore, in order to avoid randomly prior distribution, based on the empirical risk minimization (ERM) method, a data-dependent prior for the PAC-Bayes meta-learning bound algorithm is developed and the sample complexity and computational complexity are analyzed. The experiments illustrate that the proposed three PAC-Bayes bounds for meta-learning achieve a competitive generalization guarantee, and the extended PAC-Bayes bound with a data-dependent prior can achieve rapid convergence ability. [ABSTRACT FROM AUTHOR]

Fuzzy rough set is a theoretical framework of fuzzy uncertainty management, and discernibility matrix offers a mathematical foundation for algorithm construction of feature learning. The approaches of fuzzy rough set and discernibility matrix have been successfully applied in single-label learning. However, few works have been done on investigating the foundation of fuzzy rough discernibility matrix on multi-label data. There will be two pivotal problems to be addressed when using fuzzy rough discernibility matrix for multi-label data analysis. One is how to extract sample-level and label-level correlations; and the other is how to utilize the discernibility matrix for algorithm construction. For this reason, in this paper the fuzzy rough discrimination matrix is introduced to deal with the problem of multi-label feature selection. First, the significance of labels in the label space is captured based on the label correlation. Labels with different significances contribute to different weights for measuring the similarity between samples. Hence, a sample similarity matrix in the label space is computed based on the label weighting strategy. Then, a framework of a fuzzy decision system is formalized, in which the discernibility matrix of fuzzy rough sets is introduced as a foundation to evaluate the sample discrimination ability of features. Under the discernibility matrix criterion, a multi-label learning algorithm is developed to select discriminative features from multi-label data. A series of experimental analysis verifies the effectiveness and efficiency of the proposed method. [ABSTRACT FROM AUTHOR]

Deep learning is an effective tool to assist doctors with many time-consuming and error-prone medical image analytical tasks. However, deep models are shown to be vulnerable to adversarial attacks, posing significant challenges to clinical applications. Existing works regarding the robustness of deep learning models are scarce, where most of them focus on the attack of medical image classification models. In this paper, a differential evolution attack (DEAttack) method is proposed to generate adversarial examples for medical image segmentation models. Our method does not require extra information such as the network's structures and weights compared with the most widely investigated gradient-based attack methods. Additionally, benefit from the embedded differential evolution algorithm, which can preserve diversities of the optimization space. The proposed method can achieve better results than gradient-based methods, which can successfully attack the segmentation model with only perturbing a small fraction of the image pixels, demonstrating that the medical image segmentation model is more susceptible to adversarial examples. In addition to evaluating model robustness attack with public datasets, our DEAttack method was also tested on the clinical diagnostic dataset, demonstrating its superior performance and elegant process for the robustness evaluation of deep models in medical image segmentation. [ABSTRACT FROM AUTHOR]

Multi-view clustering, which aims at dividing data with similar structures into their respective groups, is a popular research subject in computer vision and machine learning. In recent years, Non-negative matrix factorization (NMF) has received constant concern in multi-view clustering due to its ability to deal with high-dimensional data. However, most existing NMF methods may fail to integrate valuable information from multi-view data adequately, and the local geometry structure in data is also not fully considered. Thus, it's still a crucial but challenging problem, which effectively extracts multi-view information while maintaining the low-dimensional geometry structure. In this paper, we propose an innovative multi-view clustering method, referred to as re-weighted multi-view clustering via triplex regularized non-negative matrix factorization (SMCTN), which is a unified framework and provides the following contributions: 1) pairwise regularization can extract complementary information between views and is suitable for both homogeneous and heterogeneous perspectives; 2) consensus regularization can process the consistent information between views; 3) graph regularization can preserve the geometric structure of data. Specifically, SMCTN applies a re-weighted strategy to assign suitable weights for multiple views according to their contributions. Besides, an effective iterative updating algorithm is developed to solve the non-convex optimization problem in SMCTN. Extensive experimental results on textual and image datasets indicate that the superior performance of the proposed method. [ABSTRACT FROM AUTHOR]

[Display omitted] • An entropy-aggregation layer proposed to strengthen reasoning ability of GCN. • An ingenious checking part based on self-training to enhance node classification. • Sufficient experiments and analyses to validate the superiority of ES-GCN. Recently, graph convolutional networks (GCNs) have achieved significant success in many graph-based learning tasks, especially for node classification, due to its excellent ability in representation learning. Nevertheless, it remains challenging for GCN models to obtain satisfying predictions on graphs where only few nodes are with known labels. In this paper, we propose a novel entropy-aware self-training algorithm to boost semi-supervised node classification on graphs with little supervised information. Firstly, an entropy-aggregation layer is developed to strengthen the reasoning ability of GCN models. To the best of our knowledge, this is the first work to combine the entropy-based random walk theory with GCN design. Furthermore, we propose an ingenious checking part to add new nodes as supervision after each training round to enhance node prediction. In particular, the checking part is designed based on aggregated features, which is demonstrated more effective than previous methods and boosts node classification significantly. The proposed algorithm is validated on six public benchmarks in comparison with several state-of-the-art baseline algorithms, and the results illustrate its excellent performance. [ABSTRACT FROM AUTHOR]

One of the main goals of Big Data research, is to find new data mining methods that are able to process large amounts of data in acceptable times. In Big Data classification, as in traditional classification, class imbalance is a common problem that must be addressed, in the case of Big Data also looking for a solution that can be applied in an acceptable execution time. In this paper we present Approx-SMOTE, a parallel implementation of the SMOTE algorithm for the Apache Spark framework. The key difference with the original SMOTE, besides parallelism, is that it uses an approximated version of k -Nearest Neighbor which makes it highly scalable. Although an implementation of SMOTE for Big Data already exists (SMOTE-BD), it uses an exact Nearest Neighbor search, which does not make it entirely scalable. Approx-SMOTE on the other hand is able to achieve up to 30 times faster run times without sacrificing the improved classification performance offered by the original SMOTE. [ABSTRACT FROM AUTHOR]

Learning causal structures from observational data is of great challenge and interest in many disciplines. Various methods have demonstrated their effectiveness for causal structure learning on different types of data, but most of them are suffered from the indeterminacy of Markov equivalence classes, especially on discrete data. A recent breakthrough formulates the problem as finding a hidden compact representation (HCR) with lower cardinality to distinguish the correct causal direction. However, method based on the HCR model is only applicable in bivariate cases. In this paper, we generalize the HCR model to multivariate cases and provide an effective likelihood-based algorithm for causal structure learning in presence of hidden compact representation. Our theoretical results show that under some weak technique conditions about the underlying causal mechanism, causal directions are still identifiable even in multivariate cases. Our empirical studies demonstrate the effectiveness of proposed methods on various types of data and structures. [ABSTRACT FROM AUTHOR]

• A new method based on Locality-Sensitive Hashing (LSH) for cluster initialization in the k-means like clustering was proposed. • A new clustering algorithm called LSH-k-representatives for handling big categorical data was developed. • Extensive experiments conducted on multiple real-world and synthetic datasets have demonstrated the effectiveness of the proposed clustering method. • The newly developed algorithm achieves comparable or better clustering performance to the existing well-known k-means like algorithms, while it is significantly more efficient by a factor of between 2× and 32×. Clustering categorical data remains a challenging problem in the era of big data, due to the difficulty in measuring dis/similarity meaningfully for categorical data and the high computational complexity of existing clustering algorithms that makes it difficult to be applied in practical use for big data mining applications. In this paper, we propose an integrated approach that incorporates the Locality-Sensitive Hashing (LSH) technique into the k -means-like clustering so as to make it capable of predicting the better initial clusters for boosting clustering effectiveness. To this end, we first utilize a data-driven dissimilarity measure for categorical data to construct a family of binary hash functions that are then used to generate the initial clusters. We also propose to use a nearest neighbor search at each iteration for cluster reassignment of data objects to improve the clustering complexity. These solutions are incorporated into the k -representatives algorithm resulting in the so-called LSH- k -representatives algorithm. Extensive experiments conducted on multiple real-world and synthetic datasets have demonstrated the effectiveness of the proposed method. It is shown that the newly developed algorithm yields comparable or better clustering results in comparison to the existing closely related works, yet it is significantly more efficient by a factor of between 2 × and 32 ×. [ABSTRACT FROM AUTHOR]