This study examines several generic properties of weighted consistent projections and indicators of inconsistency in an arbitrary finite dimensional inner product space of square matrices. In the case of weighted Frobenius inner products we present explicit formulae for them in terms of the matrix entries and weights. It extends the recent results, due to Koczkodaj et al. [Fund. Inform. 172 (2020)

We study the parameter estimation problem in mixture distributions with observational nonidentifiability: the full distribution (also containing hidden variables) is identifiable, but the marginal (observed) distribution is not. Hence global maxima of the marginal likelihood are (infinitely) degenerate and predictions of the marginal likelihood are not unique. We show how to generalize the marginal

This work proposes a novel algorithm to forecast big data time series. Based on the well-established Pattern Sequence-based Forecasting algorithm, this new approach has two major contributions to the literature. First, the improvement of the original algorithm with respect to the accuracy of predictions, and second, its transformation into the big data context, having reached meaningful results in

As we rely more and more on machine learning models for real-life decision-making, being able to understand and trust the predictions becomes ever more important. Local explainer models have recently been introduced to explain the predictions of complex machine learning models at the instance level. In this paper, we propose Local Rule-based Model Interpretability with k-optimal Associations (LoRMIkA)

Emerging issues such as privacy protection and communication limitations make it not possible to collect all data into data centers, which has driven the paradigm of big data and artificial intelligence to sink to network edge. Because of having the ability to continuously learn newly generated data from the Internet of Things and mobile devices while protecting user privacy, federated learning has

The edge minimum sum-of-squares clustering problem (E-MSSC) aims at finding p prototypes such that the sum of squares of distances from a set of vertices to their closest prototype is minimized, where a prototype is either a vertex or an interior point of an edge. This paper proposes a highly effective memetic algorithm for E-MSSC that combines a dedicated crossover operator for solution generation

The challenge of solving nonlinear equation systems is how to locate multiple optimal solutions simultaneously in a single run. To address this issue, this paper proposes a novel algorithm by combining a diversity indicator, multi-objective optimization technique, and clustering technique. Firstly, a diversity indicator is designed to maintain the diversity of the population. Then, a K-means clustering-based

Accurate negation identification is one of the most important tasks in the context of sentiment analysis. In order to correctly interpret the sentiment value of a particular expression, we need to identify whether it is in the scope of negation. While much of the work on negation detection has focused on English, we have seen recent developments that provide accurate identification of negation in other

Simple ontology alignments, largely studied in the literature, link one single entity of a source ontology to one single entity of a target ontology. One of the limitations of these alignments is, however, their lack of expressiveness, which can be overcome by complex alignments, which are composed of correspondences involving logical constructors or transformation functions. While most work on complex

Feature selection effectively reduces the dimensionality of data. For feature selection, rough set theory offers a systematic theoretical framework based on consistency measures, of which information entropy is one of the most important significance measures of attributes. However, an information-entropy-based significance measure is computationally expensive and requires repeated calculations. Although

The reconstruction of shredded documents consists of coherently arranging fragments of paper (shreds) to recover the original document(s). A great challenge in computational reconstruction is to properly evaluate the compatibility between the shreds. While traditional pixel-based approaches are not robust to real shredding, more sophisticated solutions compromise significantly time performance. The

Many applications in biomedical informatics deal with data in the tensor form. Traditional regression methods which take vectors as covariates may encounter difficulties in handling tensors due to their ultrahigh dimensionality and complex structure. In this paper, we introduce a novel sparse regularized Tucker tensor regression model to exploit the structure of tensor covariates and perform feature

This paper considers the problem of positive unlabeled (PU) learning. In this context, we propose a two-stage GAN-based model. More specifically, the main contribution is to incorporate a biased PU risk within the standard GAN discriminator loss function. In this manner, the discriminator is constrained to steer the generator to converge towards the unlabeled samples distribution while diverging from

Dynamic gesture recognition, which plays an essential role in human-computer interaction, has been widely investigated but not yet fully addressed. The challenge mainly lies in three folders: 1) to model both of the spatial appearance and the temporal evolution simultaneously; 2) to address the interference from the varied and complex background; 3) the requirement of real-time processing. In this

In this paper, we propose a deep relational network which exploits multi-scale information of facial images for kinship verification. Unlike most existing deep learning based facial kinship verification methods which employ convolutional neural networks to extract holistic features, we present a deep model to exploit facial kinship relationship from local regions. For each given pair of face images

Space target recognition is the basic task of space situational awareness and has developed significantly in the last decade. This paper proposes a hybrid convolutional neural network with partial semantic information for space target recognition, which joints the global features and partial semantic information. Firstly, we propose a two-stage target detection network based on the characteristics

Existing domain adaptation approaches focus on taking advantage of easy samples, i.e, target samples which are easier for adaptation. In previous work, tough, or hard, target samples are generally regarded as outliers or just being left to chance. As a result, the adaptation of tough target samples remains as a challenging problem in the community. In this paper, we report three novel ideas for domain

By going to millimeter wave (mmWave) we can use large scale MIMO due to short mmWave wavelength to overcome path loss by using beamforming to focus power of signal to the receiver. System structure of mmWave band is different with conventional MIMO because of large scale MIMO which is leading to use many RF‐chains. For this reason Hybrid structure have been proposed for large Scale MIMO. By going to

This article addresses the adaptive fuzzy finite‐time control problem for a class of switched nonlinear systems whose powers are positive odd rational numbers and vary with the switching signal. The fuzzy logic systems (FLSs) are used to approximate the unknown nonlinearities of the controlled systems, and then by combining backstepping control algorithm with adding a power integrator technique, an

Recently, the generative adversarial network (GAN) has attracted wide attention for various computer vision tasks. GAN provides a novel concept for image-to-image transformation by means of adversarial learning. In recent years, numerous adversarial-learning-based methods have been proposed, and impressive results have been achieved. Related reviews have mainly focused on the basic GAN model and its

As an ensemble algorithm, network boosting enjoys a powerful classification ability but suffers from the tedious and time-consuming training process. To tackle the problem, in this paper, a broad network gradient boosting system (BNGBS) is developed by integrating gradient boosting machine with broad networks, in which the classification loss caused by a base broad network is learned and eliminated

Motion averaging has recently been introduced as an effective means to tackle the registration of multi-view range scans. This approach can view parts of pair-wise motions with high reliability as an input to estimate the global motions for a multi-view registration. However, reliable pair-wise motions are not easy to confirm in most practical applications without prior knowledge. In this paper, we

A latent factor analysis (LFA)-based model has outstanding performance in extracting desired patterns from High-dimensional and Sparse (HiDS) data for building a recommender systems. However, they mostly fail in acquiring non-linear features from an HiDS matrix. An AutoEncoder (AE)-based model can address this issue efficiently, but it requires filling unknown data of an HiDS matrix with pre-assumptions

Traditional unsupervised feature selection methods usually construct a fixed similarity matrix. This matrix is sensitive to noise and becomes unreliable, which affects the performance of feature selection. The researches have shown that both the global reconstruction information and local structure information are important for feature selection. To solve the above problem effectively and make use

Weakly-supervised multi-label learning has emerged as a hot topic more recently. Most existing methods deal with such problem by learning from the data where the label assignments are incomplete while the feature information is ideal. However, in many real applications, due to the influence of occlusion, illumination and low-resolution, the acquired features are often noisy, which may reduce the robustness

In this study, we focus on understanding and mining user’s preferences and intentions via user-based aggregation in the context of a social network. Understanding preference and intention in microblog texts is more difficult and challenging than understanding such characteristics in the context of standard text. The main reason is that search history and click history are difficult to obtain due to

This paper investigates the problem of disturbance observer-based output feedback control for quadrotor unmanned aerial vehicles with external disturbances, uncertainties and input saturation. Different from the existing results, we propose a novel control algorithm towards attitude system and position system. First, considering that not all signals can be measured directly by sensors, we construct

Inspired by speech recognition, most of the recent state-of-the-art works convert scene text recognition into sequence prediction. Like most speech recognition problems, context modeling is considered as a critical component in these methods for achieving better performance. However, they usually only consider using a holistic or single-scale local sequence context, in a single dimension. Actually

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

Learning long-term dependencies remains difficult for recurrent neural networks (RNNs) despite their success in sequence modeling recently. In this paper, we propose a novel gated RNN structure, which contains only one gate. Hidden states in the proposed grouped distributor unit (GDU) are partitioned into groups. For each group, the proportion of memory to be overwritten in each state transition is

Extreme Learning Machine (ELM) is a powerful and favorable classifier used in various applications due to its fast speed and good generalization capability. However, when dealing with complex visual tasks, the shallow architecture of ELM makes it infeasible to have good performance when raw image data are directly fed in as input. Therefore, several works tried to make use of deep neural networks (DNNs)

Data often exists in subspaces embedded within a high-dimensional space. Subspace clustering seeks to group data according to the dimensions relevant to each subspace. This requires the estimation of subspaces as well as the clustering of data. Subspace clustering becomes increasingly challenging in high dimensional spaces due to the curse of dimensionality which affects reliable estimations of distances

Nowadays, the demand for segmenting different types of cells imaged by microscopes is increased tremendously. The requirements for the segmentation accuracy are becoming stricter. Because of the great diversity of cells, no traditional methods could segment various types of cells with adequate accuracy. In this paper, we aim to propose a generic approach that is capable of segmenting various types

Abstract An experimental study of laser ablation on the samples that comprise nanofilms of hafnium and zirconium dioxides on the surface of glass and silicon, and obtaining parameters of pulsed laser ablation in this work, provide new data describing the ablation mechanism. The samples were exposed to pulsed radiation from an Nd3+:YAG laser in order to measure the threshold energy density of laser

Abstract Mathematical simulations of invariant optical-digital correlator operation are performed with the LC SLM used for the input images display and for display of the correlation filter holograms. Different phase dependences on amplitude are considered, particularly the measured dependence of the LC SLM HoloEye LC 2002. A method for optimization of correlation filters to eliminate the object recognition

Abstract Structure of the fiber-optic recirculating loop memory with periodic 2R-regeneration of information flow in the optical range is designed. The modified optical fiber loop mirror for 2R-regeneration of wavelength division multiplexed return-to-zero signals is proposed. On the basis of the proposed mathematical model, using numerical modeling, the efficiency of the restoration of optical information

Abstract A method for visualization of volumetric defects in a ZnGeP2 single-crystal by digital holography method using strontium vapor laser radiation is proposed. The possibility of obtaining a volume distribution of defects with dimensions of ≥15–20 μm and their identification in a crystal is shown. The identification in a ZnGeP2 single-crystal of such volumetric defects as growth bands and needle

Abstract The paper deals with the algorithms of optimal quantization and adaptive interpolation in interpolative and hierarchical compression of multidimensional signals. An uneven quantization scale optimization algorithm is invented to tackle the unknown number of quantization levels given soft requirements for the optimization criterion. An important instance of applying the quantizer to the compression

Abstract This paper is concerned with the global Mittag-Leffler stability (GMLS) and global finite-time stability (GFTS) for fractional Hopfield neural networks (FHNNs) with Hölder neuron activation functions subject to nonlinear growth. Firstly, four functions possessing convexity are proposed, which can guarantee that four formulas with respect to the fractional derivative are established. Correspondingly

Abstract In this paper, a parallel SSD (Single Shot MultiBox Detector) fusion network based on inverted residual structure (IR-PSN) is proposed to solve the problems of the lack of extracted feature information and the unsatisfactory effect of small object detection by deep learning. Firstly, the Inverted Residual Structure (IR) is adopted into the SSD network to replace the pooling layer. The improved

Abstract Training Convolutional Neural Networks that do well in one-shot learning settings can have wide range of impacts on real-world datasets. In this paper, we explore an adversarial training method that learns a Siamese neural network in an end-to-end fashion for two models—ConvNets model that learns image embeddings from input image pair, and head model that further learns the distance between

We present ConArgLib, a C++ library implemented to help programmers solve some of the most important problems related to extension-based abstract Argumentation. The library is based on ConArg, which exploits Constraint Programming and, in particular, Gecode, a toolkit for developing constraint-based systems and applications. Given a semantics, such problems consist, for example, in enumerating all

Any evolutionary algorithm tends to end up in a local optimum. A new approach based on an evolutionary algorithm named as Diversity Driven Multi-Parent Evolutionary Algorithm with Adaptive non-uniform mutation is presented. In the proposed algorithm, Non-uniform mutation is used to maintain diversity in the explored solutions. Fitness variance, which signifies solution space aggregation, is used to

Facility layout aims to arrange a set of facilities in a site. The main objective function is to minimize the total material handling cost under production-derived constraints. This problem has received much attention during the past decades. However, these works have mainly focused on solving a 2D layout problem, dealing with the footprints of pieces of equipment. The obtained results have been then

The problem of time series anomaly detection has attracted a lot of attention due to its usefulness in various application domains. However, most of the methods proposed so far used Euclidean distance to deal with this problem. Dynamic Time Warping (DTW) distance is more suitable than Euclidean distance because of its capability in shape-based similarity checking in many practical fields, for example

Lifelong learning and adaptability are two defining aspects of biological agents. Modern reinforcement learning (RL) approaches have shown significant progress in solving complex tasks, however once training is concluded, the found solutions are typically static and incapable of adapting to new information or perturbations. While it is still not completely understood how biological brains learn and

In this paper, a mode selection network (ModeNet) is proposed to enhance deep learning-based video compression. Inspired by traditional video coding, ModeNet purpose is to enable competition among several coding modes. The proposed ModeNet learns and conveys a pixel-wise partitioning of the frame, used to assign each pixel to the most suited coding mode. ModeNet is trained alongside the different coding

Neuromorphic computing with non-volatile memory (NVM) can significantly improve performance and lower energy consumption of machine learning tasks implemented using spike-based computations and bio-inspired learning algorithms. High voltages required to operate certain NVMs such as phase-change memory (PCM) can accelerate aging in a neuron's CMOS circuit, thereby reducing the lifetime of neuromorphic

Subset selection is a popular topic in recent years and a number of subset selection methods have been proposed. Among those methods, hypervolume subset selection is widely used. Greedy hypervolume subset selection algorithms can achieve good approximations to the optimal subset. However, when the candidate set is large (e.g., an unbounded external archive with a large number of solutions), the algorithm

Biologically inspired recurrent neural networks, such as reservoir computers are of interest in designing spatio-temporal data processors from a hardware point of view due to the simple learning scheme and deep connections to Kalman filters. In this work we discuss using in-depth simulation studies a way to construct hardware reservoir computers using an analog stochastic neuron cell built from a low

This paper seeks to establish a framework for directing a society of simple, specialized, self-interested agents to solve what traditionally are posed as monolithic single-agent sequential decision problems. What makes it challenging to use a decentralized approach to collectively optimize a central objective is the difficulty in characterizing the equilibrium strategy profile of non-cooperative games

This paper analyzes regularization terms proposed recently for improving the adversarial robustness of deep neural networks (DNNs), from a theoretical point of view. Specifically, we study possible connections between several effective methods, including input-gradient regularization, Jacobian regularization, curvature regularization, and a cross-Lipschitz functional. We investigate them on DNNs with

Artificial neural networks can achieve impressive performances, and even outperform humans in some specific tasks. Nevertheless, unlike biological brains, the artificial neural networks suffer from tiny perturbations in sensory input, under various kinds of adversarial attacks. It is therefore necessary to study the origin of the adversarial vulnerability. Here, we establish a fundamental relationship

Many successful deep learning architectures are equivariant to certain transformations in order to conserve parameters and improve generalization: most famously, convolution layers are equivariant to shifts of the input. This approach only works when practitioners know a-priori symmetries of the task and can manually construct an architecture with the corresponding equivariances. Our goal is a general

A fundamental assumption of most machine learning algorithms is that the training and test data are drawn from the same underlying distribution. However, this assumption is violated in almost all practical applications: machine learning systems are regularly tested on data that are structurally different from the training set, either due to temporal correlations, particular end users, or other factors

MEMS Inertial Measurement Units (IMUs) are inexpensive and effective sensors that provide proprioceptive motion measurements for many robots and consumer devices. However, their noise characteristics and manufacturing imperfections lead to complex ramifications in classical fusion pipelines. While deep learning models provide the required flexibility to model these complexities from data, they have

We study the problem of node classification on graphs with few-shot novel labels, which has two distinctive properties: (1) There are novel labels to emerge in the graph; (2) The novel labels have only a few representative nodes for training a classifier. The study of this problem is instructive and corresponds to many applications such as recommendations for newly formed groups with only a few users

Variational inference (VI) plays an essential role in approximate Bayesian inference due to its computational efficiency and broad applicability. Crucial to the performance of VI is the selection of the associated divergence measure, as VI approximates the intractable distribution by minimizing this divergence. In this paper we propose a meta-learning algorithm to learn the divergence metric suited

We present Wiki-CS, a novel dataset derived from Wikipedia for benchmarking Graph Neural Networks. The dataset consists of nodes corresponding to Computer Science articles, with edges based on hyperlinks and 10 classes representing different branches of the field. We use the dataset to evaluate semi-supervised node classification and single-relation link prediction models. Our experiments show that

This paper introduces a unified deep neural network (DNN)-based precoder for two-user multiple-input multiple-output (MIMO) networks with five objectives: data transmission, energy harvesting, simultaneous wireless information and power transfer, physical layer (PHY) security, and multicasting. First, a rotation-based precoding is developed to solve the above problems independently. Rotation-based