In stochastic optimization problems where only noisy zeroth-order (ZO) oracles are available, the Kiefer-Wolfowitz algorithm and its randomized counterparts are widely used as gradient estimators. Existing algorithms generate the random perturbations from certain distributions with a zero mean and an isotropic (either identity or scalar) covariance matrix. In contrast, this work considers the generalization

Deep deterministic policy gradient (DDPG) is a powerful reinforcement learning algorithm for large-scale continuous controls. DDPG runs the back-propagation from the state-action value function to the actor network's parameters directly, which raises a big challenge for the compatibility of the critic network. This compatibility emphasizes that the policy evaluation is compatible with the policy improvement

A fixed-time trajectory tracking control method for uncertain robotic manipulators with input saturation based on reinforcement learning (RL) is studied. The designed RL control algorithm is implemented by a radial basis function (RBF) neural network (NN), in which the actor NN is used to generate the control strategy and the critic NN is used to evaluate the execution cost. A new nonsingular fast

The steady-state visual evoked potential (SSVEP)-based brain-computer interface (BCI) has received extensive attention in research for the less training time, excellent recognition performance, and high information translate rate. At present, most of the powerful SSVEPs detection methods are similarity measurements based on spatial filters and Pearson's correlation coefficient. Among them, the task-related

Multiple kernel clustering (MKC) optimally utilizes a group of pre-specified base kernels to improve clustering performance. Among existing MKC algorithms, the recently proposed late fusion MKC methods demonstrate promising clustering performance in various applications and enjoy considerable computational acceleration. However, we observe that the kernel partition learning and late fusion processes

This article investigates the local stability and local convergence of a class of neural network (NN) controllers with error integrals as inputs for reference tracking. It is formally proved that if the input of the NN controller consists exclusively of error terms, the control system shows a non-zero steady-state error for any constant reference except for one specific point, for both single-layer

As many deep neural network models become deeper and more complex, processing devices with stronger computing performance and communication capability are required. Following this trend, the dependence on multichip many-core systems that have high parallelism and reasonable transmission costs is on the rise. In this work, in order to improve routing performance of the system, such as routing runtime

In this article, the distributed adaptive neural network (NN) consensus fault-tolerant control (FTC) problem is studied for nonstrict-feedback nonlinear multiagent systems (NMASs) subjected to intermittent actuator faults. The NNs are applied to approximate nonlinear functions, and a NN state-observer is developed to estimate the unmeasured states. Then, to compensate for the influence of intermittent

This article addresses the problem of fast fixed-time tracking control for robotic manipulator systems subject to model uncertainties and disturbances. First, on the basis of a newly constructed fixed-time stable system, a novel faster nonsingular fixed-time sliding mode (FNFTSM) surface is developed to ensure a faster convergence rate, and the settling time of the proposed surface is independent of

Over the past few years, 2-D convolutional neural networks (CNNs) have demonstrated their great success in a wide range of 2-D computer vision applications, such as image classification and object detection. At the same time, 3-D CNNs, as a variant of 2-D CNNs, have shown their excellent ability to analyze 3-D data, such as video and geometric data. However, the heavy algorithmic complexity of 2-D

Graph convolutional networks (GCNs) have achieved great success in many applications and have caught significant attention in both academic and industrial domains. However, repeatedly employing graph convolutional layers would render the node embeddings indistinguishable. For the sake of avoiding oversmoothing, most GCN-based models are restricted in a shallow architecture. Therefore, the expressive

This article investigates the problem of relaxed exponential stabilization for coupled memristive neural networks (CMNNs) with connection fault and multiple delays via an optimized elastic event-triggered mechanism (OEEM). The connection fault of the two or some nodes can result in the connection fault of other nodes and cause iterative faults in the CMNNs. Therefore, the method of backup resources

The labeling process within a supervised learning task is usually carried out by an expert, which provides the ground truth (gold standard) for each sample. However, in many real-world applications, we typically have access to annotations provided by crowds holding different and unknown expertise levels. Learning from crowds (LFC) intends to configure machine learning paradigms in the presence of multilabelers

In this article, the neural network (NN)-based adaptive dynamic programming (ADP) event-triggered control method is presented to obtain the near-optimal control policy for the model-free finite-horizon optimal tracking control problem with constrained control input. First, using available input-output data, a data-driven model is established by a recurrent NN (RNN) to reconstruct the unknown system

This article focuses on the finite-time and fixed-time synchronization of a class of coupled discontinuous neural networks, which can be viewed as a combination of the Hindmarsh-Rose model and the Kuramoto model. To this end, under the framework of Filippov solution, a new finite-time and fixed-time stable theorem is established for nonlinear systems whose right-hand sides may be discontinuous. Moreover

Direct-optimization-based dictionary learning has attracted increasing attention for improving computational efficiency. However, the existing direct optimization scheme can only be applied to limited dictionary learning problems, and it remains an open problem to prove that the whole sequence obtained by the algorithm converges to a critical point of the objective function. In this article, we propose

Presents the table of contents for this issue of the publication.

Presents a listing of the editorial board, board of governors, current staff, committee members, and/or society editors for this issue of the publication.

This article devises a photograph-based monitoring model to estimate the real-time PM 2.5 concentrations, overcoming currently popular electrochemical sensor-based PM 2.5 monitoring methods’ shortcomings such as low-density spatial distribution and time delay. Combining the proposed monitoring model, the photographs taken by various camera devices (e.g., surveillance camera, automobile data recorder

Presents a listing of the editorial board, board of governors, current staff, committee members, and/or society editors for this issue of the publication.

These instructions give guidelines for preparing papers for this publication. Presents information for authors publishing in this journal.

Dendrite morphological neurons (DMNs) are neural models for pattern classification, where dendrites are represented by a geometric shape enclosing patterns of the same class. This study evaluates the impact of three dendrite geometries--namely, box, ellipse, and sphere--on pattern classification. In addition, we propose using smooth maximum and minimum functions to reduce the coarseness of decision

Vision-based vehicle lateral localization has been extensively studied in the literature. However, it faces great challenges when dealing with occlusion situations where the road is frequently occluded by moving/static objects. To address the occlusion problem, we propose a highly robust lateral localization framework called multilevel robust network (MLRN) in this article. MLRN utilizes three deep

Network embedding is to learn low-dimensional representations of nodes while preserving necessary information for network analysis tasks. Though representations preserving both structure and attribute features have achieved in many real-world applications, learning these representations for networks with attribute information is difficult due to the heterogeneity between structure and attribute information

In recent years, bicriteria optimization schemes for manipulator control have become preferred by researchers, given their satisfactory performance. In this article, a bicriteria weighted (BCW) scheme to remedy joint drift and minimize the infinity norm of joint velocity is proposed. The scheme adopts a novel repetitive motion index that can theoretically decouple the joint error and the position error

Anomaly detection is a key functionality in various vision systems, such as surveillance and security. In this work, we present a convolutional neural network (CNN) that supports the detection of anomaly, which has not been defined when building the model, at frame level. Our CNN, named SmithNet, is structured to simultaneously learn commonly occurring textures and their corresponding motion. Its architecture

Modeling feature interactions is of crucial significance to high-quality feature engineering on multifiled sparse data. At present, a series of state-of-the-art methods extract cross features in a rather implicit bitwise fashion and lack enough comprehensive and flexible competence of learning sophisticated interactions among different feature fields. In this article, we propose a new broad attentive

Due to limited workspace and safety requirements for practical underactuated mechanical systems, it is necessary to restrict all to-be-controlled variables and their velocities within preset ranges, avoid collisions/overshoots, and improve braking performance. However, due to fewer available control inputs, it is quite challenging to ensure error elimination and full-state constraints for both actuated/unactuated

This article proposes new inverse reinforcement learning (RL) algorithms to solve our defined Adversarial Apprentice Games for nonlinear learner and expert systems. The games are solved by extracting the unknown cost function of an expert by a learner using demonstrated expert's behaviors. We first develop a model-based inverse RL algorithm that consists of two learning stages: an optimal control learning

Spectral unmixing (SU), which refers to extracting basic features (i.e., endmembers) at the subpixel level and calculating the corresponding proportion (i.e., abundances), has become a major preprocessing technique for the hyperspectral image analysis. Since the unmixing procedure can be explained as finding a set of low-dimensional representations that reconstruct the data with their corresponding

This paper addresses the synchronization of multiple fractional-order recurrent neural networks (RNNs) with time-varying delays under event-triggered communications. Based on the assumption of the existence of strong connectivity or a spanning tree in the communication digraph, two sets of sufficient conditions are derived for achieving event-triggered synchronization. Moreover, an additional condition

This article investigates the stabilization of stochastic highly non-linear coupled systems (SHNCSs) with multiple time delays by using periodically intermittent control (PIC). It is worth noting that coefficients in SHNCSs dissatisfy the linear growth condition, which weakens the previous stability conditions. In addition, PIC and multiple time delays are first introduced into the study of highly

Accurate and rapid diagnosis of COVID-19 using chest X-ray (CXR) plays an important role in large-scale screening and epidemic prevention. Unfortunately, identifying COVID-19 from the CXR images is challenging as its radiographic features have a variety of complex appearances, such as widespread ground-glass opacities and diffuse reticular-nodular opacities. To solve this problem, we propose an adaptive

Though deep learning-based saliency detection methods have achieved gratifying performance recently, the predicted saliency maps still suffer from the boundary challenge. From the perspective of foreground-background separation, this article attempts to extract the edge information of objects by exploiting the difference between different color channels in the RGB color space and establishes a novel

Dynamic optimization is one of the model-based adaptive reinforcement learning methods, which has been widely used in industrial systems with switching mechanisms. This article presents an efficient dynamic optimization strategy to locate an optimal input and switch times for switched systems with guaranteed satisfaction for path constraints during the whole time period. In this article, we propose

Training deep neural networks (DNNs) rested heavily on efficient local solvers. Due to their local property, local solvers are sensitive to initialization and hyperparameters. In this article, a systematical method for finding multiple high-quality local optimal DNNs, based on the transformation under stability-retaining equilibria characterization (TRUST-TECH) method, is introduced. Our goal is to

Word-character lattice models have been proved to be effective for some Chinese natural language processing (NLP) tasks, in which word boundary information is fused into character sequences. However, due to the inherently unidirectional sequential nature, prior approaches have only learned sequential interactions of character-word instances but fail to capture fine-grained correlations in word-character

Fine-grained visual categorization (FGVC) is a challenging task because there are many hard examples existing between fine-grained classes which differ subtly in particular local regions. To address this issue, many methods have recourse to high-resolution source images and others adopt effective regularization like ``mixup'' or ``between class learning.'' Despite their promising achievements, mixup

This article presents a novel scheme, namely, an intermittent learning scheme based on Skinner's operant conditioning techniques that approximates the optimal policy while decreasing the usage of the communication buses transferring information. While traditional reinforcement learning schemes continuously evaluate and subsequently improve, every action taken by a specific learning agent based on received

In this article, we argue that the unsatisfactory out-of-distribution (OOD) detection performance of neural networks is mainly due to the SoftMax loss anisotropy and propensity to produce low entropy probability distributions in disagreement with the principle of maximum entropy. On the one hand, current OOD detection approaches usually do not directly fix the SoftMax loss drawbacks, but rather build

This article presents the adaptive tracking control scheme of nonlinear multiagent systems under a directed graph and state constraints. In this article, the integral barrier Lyapunov functionals (iBLFs) are introduced to overcome the conservative limitation of the barrier Lyapunov function with error variables, relax the feasibility conditions, and simultaneously solve state constrained and coupling

The Cox proportional hazard model has been widely applied to cancer prognosis prediction. Nowadays, multi-modal data, such as histopathological images and gene data, have advanced this field by providing histologic phenotype and genotype information. However, how to efficiently fuse and select the complementary information of high-dimensional multi-modal data remains challenging for Cox model, as it

Bioinspired spiking neural networks (SNNs), operating with asynchronous binary signals (or spikes) distributed over time, can potentially lead to greater computational efficiency on event-driven hardware. The state-of-the-art SNNs suffer from high inference latency, resulting from inefficient input encoding and suboptimal settings of the neuron parameters (firing threshold and membrane leak). We propose

Bayesian non-negative matrix factorization (BNMF) has been widely used in different applications. In this article, we propose a novel BNMF technique dedicated to semibounded data where each entry of the observed matrix is supposed to follow an Inverted Beta distribution. The model has two parameter matrices with the same size as the observation matrix which we factorize into a product of excitation

This article considers distributed optimization by a group of agents over an undirected network. The objective is to minimize the sum of a twice differentiable convex function and two possibly nonsmooth convex functions, one of which is composed of a bounded linear operator. A novel distributed primal-dual fixed point algorithm is proposed based on an adapted metric method, which exploits the second-order

Organizing the implicit topology of a document as a graph, and further performing feature extraction via the graph convolutional network (GCN), has proven effective in document analysis. However, existing document graphs are often restricted to expressing single-level relations, which are predefined and independent of downstream learning. A set of learnable hierarchical graphs are built to explore

This article proposes an adaptive fuzzy neural network (NN) command filtered impedance control for constrained robotic manipulators with disturbance observers. First, barrier Lyapunov functions are introduced to handle the full-state constraints. Second, the adaptive fuzzy NN is introduced to handle the unknown system dynamics and a disturbance observer is designed to eliminate the effect of unknown

The state-of-the-art reinforcement learning (RL) techniques have made innumerable advancements in robot control, especially in combination with deep neural networks (DNNs), known as deep reinforcement learning (DRL). In this article, instead of reviewing the theoretical studies on RL, which were almost fully completed several decades ago, we summarize some state-of-the-art techniques added to commonly

Hierarchical context modeling plays an important role in the response generation for multi-turn conversational systems. Previous methods mainly model context as multiple independent utterances and rely on attention mechanisms to obtain the context representation. They tend to ignore the explicit responds-to relationships between adjacent utterances and the special role that the user's latest utterance

This article investigates the collision-free cooperative formation control problem for second-order multiagent systems with unknown velocity, dynamics uncertainties, and limited reference information. An observer-based sliding mode control law is proposed to ensure both the convergence of the system's tracking error and the boundedness of the relative distance between each pair of agents. First, two

In this article, an actor-critic neural network (NN)-based online optimal adaptive regulation of a class of nonlinear continuous-time systems with known state and input delays and uncertain system dynamics is introduced. The temporal difference error (TDE), which is dependent upon state and input delays, is derived using actual and estimated value function and via integral reinforcement learning. The

In this article, we present a conceptually simple but effective framework called knowledge distillation classifier generation network (KDCGN) for zero-shot learning (ZSL), where the learning agent requires recognizing unseen classes that have no visual data for training. Different from the existing generative approaches that synthesize visual features for unseen classifiers' learning, the proposed

The bipartite formation control for the nonlinear discrete-time multiagent systems with signed digraph is considered in this article, in which the dynamics of the agents are completely unknown and multi-input multi-output (MIMO). First, the unknown nonlinear dynamic is converted into the compact-form dynamic linearization (CFDL) data model with a pseudo-Jacobian matrix (PJM). Based on the structurally

This article focuses on designing an event-triggered impulsive fault-tolerant control strategy for the stabilization of memristor-based reaction-diffusion neural networks (RDNNs) with actuator faults. Different from the existing memristor-based RDNNs with fault-free environments, actuator faults are considered here. A hybrid event-triggered and impulsive (HETI) control scheme, which combines the advantages

We study a family of adversarial (a.k.a. nonstochastic) multi-armed bandit (MAB) problems, wherein not only the player cannot observe the reward on the played arm (self-unaware player) but also it incurs switching costs when shifting to another arm. We study two cases: In Case 1, at each round, the player is able to either play or observe the chosen arm, but not both. In Case 2, the player can choose

Object detection requires plentiful data annotated with bounding boxes for model training. However, in many applications, it is difficult or even impossible to acquire a large set of labeled examples for the target task due to the privacy concern or lack of reliable annotators. On the other hand, due to the high-quality image search engines, such as Flickr and Google, it is relatively easy to obtain

In this article, we propose a novel architecture called hierarchical-task reservoir (HTR) suitable for real-time applications for which different levels of abstraction are available. We apply it to semantic role labeling (SRL) based on continuous speech recognition. Taking inspiration from the brain, this demonstrates the hierarchies of representations from perceptive to integrative areas, and we consider

Deep learning models have been able to generate rain-free images effectively, but the extension of these methods to complex rain conditions where rain streaks show various blurring degrees, shapes, and densities has remained an open problem. Among the major challenges are the capacity to encode the rain streaks and the sheer difficulty of learning multi-scale context features that preserve both global

Probabilistic topic models are considered as an effective framework for text analysis that uncovers the main topics in an unlabeled set of documents. However, the inferred topics by traditional topic models are often unclear and not easy to interpret because they do not account for semantic structures in language. Recently, a number of topic modeling approaches tend to leverage domain knowledge to

In hyperspectral image (HSI) classification task, semisupervised graph convolutional network (GCN)-based methods have received increasing attention. However, two problems still need to be addressed. The first is that the initial graph structure in the GCN-based methods is not sufficiently flexible to encode the homogenous structure similarity of HSI pixels when facing the complex scenarios induced