The goal of supervised hashing is to construct hash mappings from collections of images and semantic annotations such that semantically relevant images are embedded nearby in the learned binary hash representations. Existing deep supervised hashing approaches that employ classification frameworks with a classification training objective for learning hash codes often encode class labels as one-hot or

Abnormal behaviors in industrial systems may be early warnings on critical events that may cause severe damages to facilities and security. Thus, it is important to detect abnormal behaviors accurately and timely. However, the anomaly detection problem is hard to solve in practice, mainly due to the rareness and the expensive cost to get the labels of the anomalies. Deep generative models parameterized

Generally, the infinity-norm joint-velocity minimization (INVM) of physically constrained kinematically redundant robots can be formulated as time-variant linear programming (TVLP) with equality and inequality constraints. Zeroing neural network (ZNN) is an effective neural method for solving equality-constrained TVLP. For inequality-constrained TVLP, however, existing ZNNs become incompetent due to

The goal of multi-view clustering is to partition samples into different subsets according to their diverse features. Previous multi-view clustering methods mainly exist two forms: multi-view spectral clustering and multi-view matrix factorization. Although they have shown excellent performance in many occasions, there are still many disadvantages. For example, multi-view spectral clustering usually

Classification methods for streaming data are not new, but very few current frameworks address all three of the most common problems with these tasks: concept drift, noise, and the exorbitant costs associated with labeling the unlabeled instances in data streams. Motivated by this gap in the field, we developed an active learning framework based on a dual-query strategy and Ebbinghaus's law of human

This article investigates the distributed fault-tolerant time-varying formation control problem for multiple unmanned airships (UAs) against limited communication ranges and input saturation to achieve the safe observation of a smart city. To address the strongly nonlinear functions caused by the time-varying formation flight with limited communication ranges and bias faults, intelligent adaptive learning

Good generalization performance is the fundamental goal of any machine learning algorithm. Using the uniform stability concept, this article theoretically proves that the choice of loss function impacts the generalization performance of a trained deep neural network (DNN). The adopted stability-based framework provides an effective tool for comparing the generalization error bound with respect to the

Direct convolution methods are now drawing increasing attention as they eliminate the additional storage demand required by indirect convolution algorithms (i.e., the transformed matrix generated by the im2col convolution algorithm). Nevertheless, the direct methods require special input-output tensor formatting, leading to extra time and memory consumption to get the desired data layout. In this article

This article is concerned with passivity analysis of neural networks with a time-varying delay. Several techniques in the domain are improved to establish the new passivity criterion with less conservatism. First, a Lyapunov-Krasovskii functional (LKF) is constructed with two general delay-product-type terms which contain any chosen degree of polynomials in time-varying delay. Second, a general convexity

In this article, the tracking control problem of event-triggered multigradient recursive reinforcement learning is investigated for nonlinear multiagent systems (MASs). Attention is focused on the distributed reinforcement learning approach for MASs. The critic neural network (NN) is applied to estimate the long-term strategic utility function, and the actor NN is designed to approximate the uncertain

The issue of finite-time state estimation is studied for discrete-time Markovian bidirectional associative memory neural networks. The asymmetrical system mode-dependent (SMD) time-varying delays (TVDs) are considered, which means that the interval of TVDs is SMD. Because the sensors are inevitably influenced by the measurement environments and indirectly influenced by the system mode, a Markov chain

The generative adversarial networks (GANs) in continual learning suffer from catastrophic forgetting. In continual learning, GANs tend to forget about previous generation tasks and only remember the tasks they just learned. In this article, we present a novel conditional GAN, called the gradients orthogonal projection GAN (GopGAN), which updates the weights in the orthogonal subspace of the space spanned

Passenger-flow anomaly detection and prediction are essential tasks for intelligent operation of the metro system. Accurate passenger-flow representation is the foundation of them. However, spatiotemporal dependencies, complex dynamic changes, and anomalies of passenger-flow data bring great challenges to data representation. Taking advantage of the time-varying characteristics of data, we propose

Most modern learning problems are highly overparameterized, i.e., have many more model parameters than the number of training data points. As a result, the training loss may have infinitely many global minima (parameter vectors that perfectly ``interpolate'' the training data). It is therefore imperative to understand which interpolating solutions we converge to, how they depend on the initialization

Discriminating small moving objects within complex visual environments is a significant challenge for autonomous micro-robots that are generally limited in computational power. By exploiting their highly evolved visual systems, flying insects can effectively detect mates and track prey during rapid pursuits, even though the small targets equate to only a few pixels in their visual field. The high degree

In this article, the bipartite synchronization issue is studied for a class of discrete-time coupled switched neural networks with antagonistic interactions via a distributed dynamic event-triggered control scheme. Essentially different from most current literature, the topology switching of the investigated signed graph is governed by a double-layer switching signal, which integrates a flexible deterministic

Essential decision-making tasks such as power management in future vehicles will benefit from the development of artificial intelligence technology for safe and energy-efficient operations. To develop the technique of using neural network and deep learning in energy management of the plug-in hybrid vehicle and evaluate its advantage, this article proposes a new adaptive learning network that incorporates

Sarcasm is a sophisticated construct to express contempt or ridicule. It is well-studied in multiple disciplines (e.g., neuroanatomy and neuropsychology) but is still in its infancy in computational science (e.g., Twitter sarcasm detection). In contrast to previous methods that are usually geared toward a single discipline, we focus on the multidisciplinary cross-innovation, i.e., improving embryonic

This article focuses on the problem of adaptive bipartite output tracking for a class of heterogeneous linear multiagent systems (MASs) by asynchronous edge-event-triggered communications under jointly connected signed topologies. By designing the observers to estimate the states of followers and the dynamic compensators to estimate the states of zero input and nonzero input leader, respectively, the

In this article, we address the disturbance/uncertainty estimation of maritime autonomous surface ships (MASSs) with unknown internal dynamics, unknown external disturbances, and unknown input gains. In contrast to existing disturbance observers where some prior knowledge on kinetic model parameters such as the control input gains is available in advance, reduced- and full-order data-driven adaptive

This article analyzes the exponentially stable problem of neural networks (NNs) with two additive time-varying delay components. Disparate from the previous solutions on this similar model, switching ideas, that divide the time-varying delay intervals and treat the small intervals as switching signals, are introduced to transfer the studied problem into a switching problem. Besides, delay-dependent

This article studies the problem of finite-time stability (FTS) and finite-time contractive stability (FTCS) for nonlinear impulsive systems, where the possibility of time delay in impulses is fully considered. Some sufficient conditions for FTS/FTCS are constructed in the framework of Lyapunov function methods. A relationship between impulsive frequency and the time delay existing in impulses is established

Existing domain adaptation approaches often try to reduce distribution difference between source and target domains and respect domain-specific discriminative structures by some distribution [e.g., maximum mean discrepancy (MMD)] and discriminative distances (e.g., intra-class and inter-class distances). However, they usually consider these losses together and trade off their relative importance by

Multiple kernel clustering (MKC) has recently achieved remarkable progress in fusing multisource information to boost the clustering performance. However, the O( n²) memory consumption and O( n³ ) computational complexity prohibit these methods from being applied into median- or large-scale applications, where n denotes the number of samples. To address these issues, we carefully redesign the formulation

Reinforcement learning with safety constraints is promising for autonomous vehicles, of which various failures may result in disastrous losses. In general, a safe policy is trained by constrained optimization algorithms, in which the average constraint return as a function of states and actions should be lower than a predefined bound. However, most existing safe learning-based algorithms capture states

In this article, a combined gradient descent-Barzilai Borwein (GD-BB) algorithm and radial basis function neural network (RBFNN) output tracking control strategy was proposed for a family of nonlinear systems with unknown drift function and control input gain function. In such a method, a neural network (NN) is used to approximate the controller directly. The main merits of the proposed strategy are

Portfolio selection is one of the important issues in financial investments. This article is concerned with portfolio selection based on collaborative neurodynamic optimization. The classic Markowitz mean-variance (MV) framework and its variant mean conditional value-at-risk (CVaR) are formulated as minimax and biobjective portfolio selection problems. Neurodynamic approaches are then applied for solving

This article investigates the problem of path following for the underactuated unmanned surface vehicles (USVs) subject to state constraints. A useful control algorithm is proposed by combining the backstepping technique, adaptive dynamic programming (ADP), and the event-triggered mechanism. The presented approach consists of three modules: guidance law, dynamic controller, and event triggering. First

Change detection (CD), as one of the central problems in Earth observation, has attracted a lot of research interest over recent decades. Due to the rapid development of satellite sensors in recent years, we have witnessed an enrichment of the CD source data with the availability of very-high-resolution (VHR) multispectral imagery, which provides abundant change clues. However, precisely locating real

In this article, the adaptive neural backstepping control approaches are designed for uncertain stochastic nonlinear systems with full-state constraints. According to the symmetry of constraint boundary, two cases of controlled systems subject to symmetric and asymmetric constraints are studied, respectively. Then, corresponding adaptive neural controllers are developed by virtue of backstepping design

This article proposes a fault-tolerant adaptive multigradient recursive reinforcement learning (RL) event-triggered tracking control scheme for strict-feedback discrete-time multiagent systems. The multigradient recursive RL algorithm is used to avoid the local optimal problem that may exist in the gradient descent scheme. Different from the existing event-triggered control results, a new lemma about

In this work, we investigate the use of three information-theoretic quantities--entropy, mutual information with the class variable, and a class selectivity measure based on Kullback-Leibler (KL) divergence--to understand and study the behavior of already trained fully connected feedforward neural networks (NNs). We analyze the connection between these information-theoretic quantities and classification

Reinforcement learning (RL) agents learn by exploring the environment and then exploiting what they have learned. This frees the human trainers from having to know the preferred action or intrinsic value of each encountered state. The cost of this freedom is that RL is slower and more unstable than supervised learning. We explore the possibility that ensemble methods can remedy these shortcomings by

Finding a consensus embedding from multiple views is the mainstream task in multiview graph-based clustering, in which the key problem is to handle the inconsistence among multiple views. In this article, we consider clustering effectiveness and practical applicability collectively, and propose a parameter-free model to alleviate the inconsistence of multiple views cleverly. To be specific, the proposed

We solve an important and challenging cooperative navigation control problem, Multiagent Navigation to Unassigned Multiple targets (MNUM) in unknown environments with minimal time and without collision. Conventional methods are based on multiagent path planning that requires building an environment map and expensive real-time path planning computations. In this article, we formulate MNUM as a stochastic

Textbook question answering (TQA) is a task that one should answer non-diagram and diagram questions accurately, given a large context which consists of abundant diagrams and essays. Although lots of studies have made significant progress in the natural image question answering (QA), they are not applicable to comprehending diagrams and reasoning over the long multimodal context. To address the above

The well-known backpropagation learning algorithm is probably the most popular learning algorithm in artificial neural networks. It has been widely used in various applications of deep learning. The backpropagation algorithm requires a separate feedback network to back propagate errors. This feedback network must have the same topology and connection strengths (weights) as the feed-forward network

Deep neural networks (DNNs) have been demonstrating phenomenal success in many real-world applications. However, recent works show that DNN's decision can be easily misguided by adversarial examples-the input with imperceptible perturbations crafted by an ill-disposed adversary, causing the ever-increasing security concerns for DNN-based systems. Unfortunately, current defense techniques face the following

Fusing low dynamic range (LDR) for high dynamic range (HDR) images has gained a lot of attention, especially to achieve real-world application significance when the hardware resources are limited to capture images with different exposure times. However, existing HDR image generation by picking the best parts from each LDR image often yields unsatisfactory results due to either the lack of input images

In transfer learning model, the source domain samples and target domain samples usually share the same class labels but have different distributions. In general, the existing transfer learning algorithms ignore the interclass differences and intraclass similarities across domains. To address these problems, this article proposes a transfer learning algorithm based on discriminative Fisher embedding

Trajectory or path planning is a fundamental issue in a wide variety of applications. In this article, we show that it is possible to solve path planning on a maze for multiple start point and endpoint highly efficiently with a novel configuration of multilayer networks that use only weighted pooling operations, for which no network training is needed. These networks create solutions, which are identical

A data-driven distributed formation control algorithm is proposed for an unknown heterogeneous non-affine nonlinear discrete-time MIMO multi-agent system (MAS) with sensor fault. For the considered unknown MAS, the dynamic linearization technique in model-free adaptive control (MFAC) theory is used to transform the unknown MAS into an equivalent virtual dynamic linearization data model. Then using

In this article, a new projection neural network (PNN) for solving L₁-minimization problem is proposed, which is based on classic PNN and sliding mode control technique. Furthermore, the proposed network can be used to make sparse signal reconstruction and image reconstruction. First, a sign function is introduced into the PNN model to design fixed-time PNN (FPNN). Then, under the condition that the

Recently, stochastic hard thresholding (HT) optimization methods [e.g., stochastic variance reduced gradient hard thresholding (SVRGHT)] are becoming more attractive for solving large-scale sparsity/rank-constrained problems. However, they have much higher HT oracle complexities, especially for high-dimensional data or large-scale matrices. To address this issue and inspired by the well-known Gradient

In this work, an adaptive neural network (NN) optimized output-feedback control problem is studied for a class of stochastic nonlinear systems with unknown nonlinear dynamics, input saturation, and state constraints. A nonlinear state observer is designed to estimate the unmeasured states, and the NNs are used to approximate the unknown nonlinear functions. Under the framework of the backstepping technique

In this article, a rapid sensor fault diagnosis (SFD) method is presented for a class of nonlinear systems. First, by exploiting the linear adaptive observer technology and the deterministic learning method (DLM), an adaptive neural network (NN) observer is constructed to capture the information of the unknown sensor fault function. Second, when the NN input orbit is a period or recurrent one, the

One-shot semantic segmentation poses the challenging task of segmenting object regions from unseen categories with only one annotated example as guidance. Thus, how to effectively construct robust feature representations from the guidance image is crucial to the success of one-shot semantic segmentation. To this end, we propose in this article a simple, yet effective approach named rich embedding features

Clustering algorithms based on deep neural networks have been widely studied for image analysis. Most existing methods require partial knowledge of the true labels, namely, the number of clusters, which is usually not available in practice. In this article, we propose a Bayesian nonparametric framework, deep nonparametric Bayes (DNB), for jointly learning image clusters and deep representations in

Hierarchical reinforcement learning (HRL) is a promising approach to perform long-horizon goal-reaching tasks by decomposing the goals into subgoals. In a holistic HRL paradigm, an agent must autonomously discover such subgoals and also learn a hierarchy of policies that uses them to reach the goals. Recently introduced end-to-end HRL methods accomplish this by using the higher-level policy in the

In online learning, the dynamic regret metric chooses the reference oracle that may change over time, while the typical (static) regret metric assumes the reference solution to be constant over the whole time horizon. The dynamic regret metric is particularly interesting for applications, such as online recommendation (since the customers' preference always evolves over time). While the online gradient

This article develops several centralized and collective neurodynamic approaches for sparse signal reconstruction by solving the L₁-minimization problem. First, two centralized neurodynamic approaches are designed based on the augmented Lagrange method and the Lagrange method with derivative feedback and projection operator. Then, the optimality and global convergence of them are derived. In addition

Scene graph generation (SGGen) is a challenging task due to a complex visual context of an image. Intuitively, the human visual system can volitionally focus on attended regions by salient stimuli associated with visual cues. For example, to infer the relationship between man and horse, the interaction between human leg and horseback can provide strong visual evidence to predict the predicate ride

One of the significant tasks in remaining useful life (RUL) prediction is to find a good health indicator (HI) that can effectively represent the degradation process of a system. However, it is difficult for traditional data-driven methods to construct accurate HIs due to their incomprehensive consideration of temporal dependencies within the monitoring data, especially for aeroengines working under

Existing methods for tensor completion (TC) have limited ability for characterizing low-rank (LR) structures. To depict the complex hierarchical knowledge with implicit sparsity attributes hidden in a tensor, we propose a new multilayer sparsity-based tensor decomposition (MLSTD) for the low-rank tensor completion (LRTC). The method encodes the structured sparsity of a tensor by the multiple-layer

For solving dynamic generalized Lyapunov equation, two robust finite-time zeroing neural network (RFTZNN) models with stationary and nonstationary parameters are generated through the usage of an improved sign-bi-power (SBP) activation function (AF). Taking differential errors and model implementation errors into account, two corresponding perturbed RFTZNN models are derived to facilitate the analyses

In this article, a new iterative spiking adaptive dynamic programming (SADP) method based on the Poisson process is developed to solve optimal impulsive control problems. For a fixed time interval, combining the Poisson process and the maximum likelihood estimation (MLE), the three-tuple of state, spiking interval, and probability of Poisson distribution can be computed, and then, the iterative value

The Preisach model and the neural networks are two of the most popular strategies to model hysteresis. In this article, we first mathematically prove that the rate-independent Preisach model is actually a diagonal recurrent neural network (dRNN) with the binary step activation function. For the first time, the hysteresis nature and conditions of the classical dRNN with the tanh activation function

This work addresses a finite-time tracking control issue for a class of nonlinear systems with asymmetric time-varying output constraints and input nonlinearities. To guarantee the finite-time convergence of tracking errors, a novel finite-time command filtered backstepping approach is presented by using the command filtered backstepping technique, finite-time theory, and barrier Lyapunov functions

In this article, a novel composite hierarchical antidisturbance control (CHADC) algorithm aided by the information-theoretic learning (ITL) technique is developed for non-Gaussian stochastic systems subject to dynamic disturbances. The whole control process consists of some time-domain intervals called batches. Within each batch, a CHADC scheme is applied to the system, where a disturbance observer

Cross-modality visible-infrared person reidentification (VI-ReID), which aims to retrieve pedestrian images captured by both visible and infrared cameras, is a challenging but essential task for smart surveillance systems. The huge barrier between visible and infrared images has led to the large cross-modality discrepancy and intraclass variations. Most existing VI-ReID methods tend to learn discriminative