Search

In this paper, a two-layer recurrent neural network is proposed to solve the nonsmooth convex optimization problem subject to convex inequality and linear equality constraints. Compared with existing neural network models, the proposed neural network has a low model complexity and avoids penalty parameters. It is proved that from any initial point, the state of the proposed neural network reaches the equality feasible region in finite time and stays there thereafter. Moreover, the state is unique if the initial point lies in the equality feasible region. The equilibrium point set of the proposed neural network is proved to be equivalent to the Karush–Kuhn–Tucker optimality set of the original optimization problem. It is further proved that the equilibrium point of the proposed neural network is stable in the sense of Lyapunov. Moreover, from any initial point, the state is proved to be convergent to an equilibrium point of the proposed neural network. Finally, as applications, the proposed neural network is used to solve nonlinear convex programming with linear constraints and L1 -norm minimization problems. [ABSTRACT FROM AUTHOR]

This paper presents the design of an optimal controller for solving tracking problems subject to unmeasurable disturbances and unknown system dynamics using reinforcement learning (RL). Many existing RL control methods take disturbance into account by directly measuring it and manipulating it for exploration during the learning process, thereby preventing any disturbance induced bias in the control estimates. However, in most practical scenarios, disturbance is neither measurable nor manipulable. The main contribution of this article is the introduction of a combination of a bias compensation mechanism and the integral action in the Q-learning framework to remove the need to measure or manipulate the disturbance, while preventing disturbance induced bias in the optimal control estimates. A bias compensated Q-learning scheme is presented that learns the disturbance induced bias terms separately from the optimal control parameters and ensures the convergence of the control parameters to the optimal solution even in the presence of unmeasurable disturbances. Both state feedback and output feedback algorithms are developed based on policy iteration (PI) and value iteration (VI) that guarantee the convergence of the tracking error to zero. The feasibility of the design is validated on a practical optimal control application of a heating, ventilating, and air conditioning (HVAC) zone controller. [ABSTRACT FROM AUTHOR]

Prospective authors are requested to submit new, unpublished manuscripts for inclusion in the upcoming event described in this call for papers. [ABSTRACT FROM AUTHOR]

In this paper, an adaptive admittance control scheme is developed for robots to interact with time-varying environments. Admittance control is adopted to achieve a compliant physical robot–environment interaction, and the uncertain environment with time-varying dynamics is defined as a linear system. A critic learning method is used to obtain the desired admittance parameters based on the cost function composed of interaction force and trajectory tracking without the knowledge of the environmental dynamics. To deal with dynamic uncertainties in the control system, a neural-network (NN)-based adaptive controller with a dynamic learning framework is developed to guarantee the trajectory tracking performance. Experiments are conducted and the results have verified the effectiveness of the proposed method. [ABSTRACT FROM AUTHOR]

Dropout and DropConnect are two techniques to facilitate the regularization of neural network models, having achieved the state-of-the-art results in several benchmarks. In this paper, to improve the generalization capability of spiking neural networks (SNNs), the two drop techniques are first applied to the state-of-the-art SpikeProp learning algorithm resulting in two improved learning algorithms called SPDO (SpikeProp with Dropout) and SPDC (SpikeProp with DropConnect). In view that a higher membrane potential of a biological neuron implies a higher probability of neural activation, three adaptive drop algorithms, SpikeProp with Adaptive Dropout (SPADO), SpikeProp with Adaptive DropConnect (SPADC), and SpikeProp with Group Adaptive Drop (SPGAD), are proposed by adaptively adjusting the keep probability for training SNNs. A convergence theorem for SPDC is proven under the assumptions of the bounded norm of connection weights and a finite number of equilibria. In addition, the five proposed algorithms are carried out in a collaborative neurodynamic optimization framework to improve the learning performance of SNNs. The experimental results on the four benchmark data sets demonstrate that the three adaptive algorithms converge faster than SpikeProp, SPDO, and SPDC, and the generalization errors of the five proposed algorithms are significantly smaller than that of SpikeProp. Furthermore, the experimental results also show that the five algorithms based on collaborative neurodynamic optimization can be improved in terms of several measures. [ABSTRACT FROM AUTHOR]

Generative adversarial networks (GANs) for (generalized) zero-shot learning (ZSL) aim to generate unseen image features when conditioned on unseen class embeddings, each of which corresponds to one unique category. Most existing works on GANs for ZSL generate features by merely feeding the seen image feature/class embedding (combined with random Gaussian noise) pairs into the generator/discriminator for a two-player minimax game. However, the structure consistency of the distributions among the real/fake image features, which may shift the generated features away from their real distribution to some extent, is seldom considered. In this paper, to align the weights of the generator for better structure consistency between real/fake features, we propose a novel multigraph adaptive GAN (MGA-GAN). Specifically, a Wasserstein GAN equipped with a classification loss is trained to generate discriminative features with structure consistency. MGA-GAN leverages the multigraph similarity structures between sliced seen real/fake feature samples to assist in updating the generator weights in the local feature manifold. Moreover, correlation graphs for the whole real/fake features are adopted to guarantee structure correlation in the global feature manifold. Extensive evaluations on four benchmarks demonstrate well the superiority of MGA-GAN over its state-of-the-art counterparts. [ABSTRACT FROM AUTHOR]

A nomaly detection aims at identifying data points which are rare or significantly different from the majority of data points. Many techniques are explored to build highly efficient and effective anomaly detection systems, but they are confronted with many difficulties when dealing with complex data, such as failing to capture intricate feature interactions or extract good feature representations. Deep-learning techniques have shown very promising performance in tackling different types of complex data in a broad range of tasks/problems, including anomaly detection. To address this new trend, we organized this Special Issue on Deep Learning for Anomaly Detection to cover the latest advancements of developing deep-learning techniques specially designed for anomaly detection. This editorial note provides an overview of the paper submissions to the Special Issue, and briefly introduces each of the accepted articles. [ABSTRACT FROM AUTHOR]

Anomaly detection is one of the most active research areas in various critical domains, such as healthcare, fintech, and public security. However, little attention has been paid to scholarly data, that is, anomaly detection in a citation network. Citation is considered as one of the most crucial metrics to evaluate the impact of scientific research, which may be gamed in multiple ways. Therefore, anomaly detection in citation networks is of significant importance to identify manipulation and inflation of citations. To address this open issue, we propose a novel deep graph learning model, namely graph learning for anomaly detection (GLAD), to identify anomalies in citation networks. GLAD incorporates text semantic mining to network representation learning by adding both node attributes and link attributes via graph neural networks (GNNs). It exploits not only the relevance of citation contents, but also hidden relationships between papers. Within the GLAD framework, we propose an algorithm called Citation PUrpose (CPU) to discover the purpose of citation based on citation context. The performance of GLAD is validated through a simulated anomalous citation dataset. Experimental results demonstrate the effectiveness of GLAD on the anomalous citation detection task. [ABSTRACT FROM AUTHOR]

In this paper, we are concerned with the finite-time synchronization of a class of inertial neural networks with time delays. Without applying some finite-time stability theorems, which are widely applied to studying the finite-time synchronization for neural networks, by constructing two Lyapunov functions and using integral inequality method, two sufficient conditions on the finite-time synchronization for a class of inertial neural networks with time delays are derived. Considering that the method and research results of the finite-time synchronization are different from some existing works, this paper extends the works on the finite-time synchronization of neural networks. [ABSTRACT FROM AUTHOR]

In this paper, we propose a label-less learning for emotion cognition (LLEC) to achieve the utilization of a large amount of unlabeled data. We first inspect the unlabeled data from two perspectives, i.e., the feature layer and the decision layer. By utilizing the similarity model and the entropy model, this paper presents a hybrid label-less learning that can automatically label data without human intervention. Then, we design an enhanced hybrid label-less learning to purify the automatic labeled data. To further improve the accuracy of emotion detection model and increase the utilization of unlabeled data, we apply enhanced hybrid label-less learning for multimodal unlabeled emotion data. Finally, we build a real-world test bed to evaluate the LLEC algorithm. The experimental results show that the LLEC algorithm can improve the accuracy of emotion detection significantly. [ABSTRACT FROM AUTHOR]

This paper aims to give a design strategy on the prescribed performance $ {H_{\infty }}$ tracking control problem for a class of strict-feedback stochastic nonlinear systems based on the backstepping technique. Generally, by using the backstepping design method, the stochastic nonlinear systems can only be made to be bounded in probability and it is difficult to achieve the $ {H_{\infty }}$ performance criterion due to the positive constant term appeared in the stability analysis. Thus, a novel concept with regard to the bounded- $ {H_{\infty }}$ performance is proposed in this paper to overcome the design difficulty. By using the new concept and the adaptive neural network technique as well as Gronwall inequality, an adaptive neural network prescribed performance bounded- $ {H_{\infty }}$ tracking controller is designed. Therein, neural networks are used to approximate the unknown packaged nonlinear functions. The assumption that the approximation errors of neural networks are square-integrable in some literature is eliminated. The designed controller guarantees that all the signals in the closed-loop stochastic nonlinear systems are bounded in probability, the tracking error is constrained into an adjustable neighborhood of the origin with the prescribed performance bounds, and the controlled system has a given $ {H_{\infty }}$ disturbance attenuation performance for external disturbances. Finally, the simulation results are provided to illustrate the effectiveness and feasibility of the proposed approach. [ABSTRACT FROM AUTHOR]

This paper investigates the automatic exploration problem under the unknown environment, which is the key point of applying the robotic system to some social tasks. The solution to this problem via stacking decision rules is impossible to cover various environments and sensor properties. Learning-based control methods are adaptive for these scenarios. However, these methods are damaged by low learning efficiency and awkward transferability from simulation to reality. In this paper, we construct a general exploration framework via decomposing the exploration process into the decision, planning, and mapping modules, which increases the modularity of the robotic system. Based on this framework, we propose a deep reinforcement learning-based decision algorithm that uses a deep neural network to learning exploration strategy from the partial map. The results show that this proposed algorithm has better learning efficiency and adaptability for unknown environments. In addition, we conduct the experiments on the physical robot, and the results suggest that the learned policy can be well transferred from simulation to the real robot. [ABSTRACT FROM AUTHOR]

This paper presents the multistability analysis of almost periodic state solutions for memristive Cohen–Grossberg neural networks (MCGNNs) with both distributed delay and discrete delay. The activation function of the considered MCGNNs is generalized to be nonmonotonic and nonpiecewise linear. It is shown that the MCGNNs with $n$ -neuron have $(K+1)^{n}$ locally exponentially stable almost periodic solutions, where nature number $K$ depends on the geometrical structure of the considered activation function. Compared with the previous related works, the number of almost periodic state solutions of the MCGNNs is extensively increased. The obtained conclusions in this paper are also capable of studying the multistability of equilibrium points or periodic solutions of the MCGNNs. Moreover, the enlarged attraction basins of attractors are estimated based on original partition. Some comparisons and convincing numerical examples are provided to substantiate the superiority and efficiency of obtained results. [ABSTRACT FROM AUTHOR]

This paper is concerned with the stubborn state estimation of delayed neural networks that subject to a general class of disturbances in measurements, including outliers and impulsive disturbances as its special cases. This class of disturbances may be unbounded, irregular, and assorted; therefore, they can hardly be suppressed by existing identification-based estimation approaches. In this paper, a stubborn state estimator is constructed by intentionally devising a saturation scheme on the injection of output estimation error. The embedded saturation can effectively resist the influences from these measurement disturbances by saturating them. Moreover, the saturation threshold in the designed scheme is not constant but governed by a dynamic equation with parameters to be designed. Benefiting from this adaptiveness, the estimator obtains more freedom in dealing with various disturbances. By combining a novel Lyapunov functional, the generalized sector condition and two latest integral inequalities, a delay-dependent criterion is derived in a less conservative way to check whether the estimation error system with this dynamic saturation is globally stable. A sufficient condition with two tuning scalars is further provided to codesign the gain of the state estimator and the evolution law of the saturation threshold. Finally, two numerical examples are used to illustrate the stubbornness of this state estimator in the presence of measurement outliers or impulsive disturbances. [ABSTRACT FROM AUTHOR]

This paper addresses the biological plausibility of both backpropagation (BP) and contrastive Hebbian learning (CHL) used in the Boltzmann machines. The main claim of this paper is that CHL is a general learning algorithm that can be used to steer feedforward networks toward desirable outcomes, and steer them away from undesirable outcomes without any need for the specialized feedback circuit of BP or the symmetric connections used by the Boltzmann machines. After adding perturbations during the learning phase to all the neurons in the network, multiple feedforward outcomes are classified into Hebbian and anti-Hebbian sets based on the network predictions. The algorithm is applied to networks when optimizing a loss objective where BP excels and is also applied to networks with stochastic binary outputs where BP cannot be easily applied. The power of the proposed algorithm lies in its simplicity where both learning and gradient estimation through stochastic binary activations are combined into a single local Hebbian rule. We will also show that both Hebbian and anti-Hebbian correlations are evaluated from the readily available signals that are fundamentally different from CHL used in the Boltzmann machines. We will demonstrate that the new learning paradigm where Hebbian/anti-Hebbian correlations are based on correct/incorrect predictions is a powerful concept that separates this paper from other biologically inspired learning algorithms. [ABSTRACT FROM AUTHOR]

The space of graphs is often characterized by a nontrivial geometry, which complicates learning and inference in practical applications. A common approach is to use embedding techniques to represent graphs as points in a conventional Euclidean space, but non-Euclidean spaces have often been shown to be better suited for embedding graphs. Among these, constant-curvature Riemannian manifolds (CCMs) offer embedding spaces suitable for studying the statistical properties of a graph distribution, as they provide ways to easily compute metric geodesic distances. In this paper, we focus on the problem of detecting changes in stationarity in a stream of attributed graphs. To this end, we introduce a novel change detection framework based on neural networks and CCMs, which takes into account the non-Euclidean nature of graphs. Our contribution in this paper is twofold. First, via a novel approach based on adversarial learning, we compute graph embeddings by training an autoencoder to represent graphs on CCMs. Second, we introduce two novel change detection tests operating on CCMs. We perform experiments on synthetic data, as well as two real-world application scenarios: the detection of epileptic seizures using functional connectivity brain networks and the detection of hostility between two subjects, using human skeletal graphs. Results show that the proposed methods are able to detect even small changes in a graph-generating process, consistently outperforming approaches based on Euclidean embeddings. [ABSTRACT FROM AUTHOR]

This paper proposes a novel end-to-end learning model, called skip-connected covariance (SCCov) network, for remote sensing scene classification (RSSC). The innovative contribution of this paper is to embed two novel modules into the traditional convolutional neural network (CNN) model, i.e., skip connections and covariance pooling. The advantages of newly developed SCCov are twofold. First, by means of the skip connections, the multi-resolution feature maps produced by the CNN are combined together, which provides important benefits to address the presence of large-scale variance in RSSC data sets. Second, by using covariance pooling, we can fully exploit the second-order information contained in such multi-resolution feature maps. This allows the CNN to achieve more representative feature learning when dealing with RSSC problems. Experimental results, conducted using three large-scale benchmark data sets, demonstrate that our newly proposed SCCov network exhibits very competitive or superior classification performance when compared with the current state-of-the-art RSSC techniques, using a much lower amount of parameters. Specifically, our SCCov only needs 10% of the parameters used by its counterparts. [ABSTRACT FROM AUTHOR]

Because of a powerful temporal-difference (TD) with $\lambda $ [TD($\lambda $)] learning method, this paper presents a novel $n$ -step adaptive dynamic programming (ADP) architecture that combines TD($\lambda $) with regular TD learning for solving optimal control problems with reduced iterations. In contrast with a backward view learning of TD($\lambda $) that is required an extra parameter named eligibility traces to update at the end of each episode (offline training), the new design in this paper has forward view learning, which is updated at each time step (online training) without needing the eligibility trace parameter in various applications without mathematical models. Therefore, the new design is called the online model-free $n$ -step action-dependent (AD) heuristic dynamic programming [NSHDP($\lambda $)]. NSHDP($\lambda $) has three neural networks: the critic network (CN) with regular one-step TD [TD(0)], the CN with $n$ -step TD learning [or TD($\lambda $)], and the actor network (AN). Because the forward view learning does not require any extra eligibility traces associated with each state, the NSHDP($\lambda $) architecture has low computational costs and is memory efficient. Furthermore, the stability is proven for NSHDP($\lambda $) under certain conditions by using Lyapunov analysis to obtain the uniformly ultimately bounded (UUB) property. We compare the results with the performance of HDP and traditional action-dependent HDP($\lambda $) [ADHDP($\lambda $)] with different $\lambda $ values. Moreover, a complex nonlinear system and 2-D maze problem are two simulation benchmarks in this paper, and the third one is an inverted pendulum simulation benchmark, which is presented in the supplemental material part of this paper. NSHDP($\lambda $) performance is examined and compared with other ADP methods. [ABSTRACT FROM AUTHOR]

This paper deals with regression problems, in which the nonsmooth target is assumed to switch between different operating modes. Specifically, piecewise smooth (PWS) regression considers target functions switching deterministically via a partition of the input space, while switching regression considers arbitrary switching laws. This paper derives generalization error bounds in these two settings by following the approach based on Rademacher complexities. For PWS regression, our derivation involves a chaining argument and a decomposition of the covering numbers of PWS classes in terms of the ones of their component function classes and the capacity of the classifier partitioning the input space. This yields error bounds with a radical dependence on the number of modes. For switching regression, the decomposition can be performed directly at the level of the Rademacher complexities, which yields bounds with a linear dependence on the number of modes. By using once more chaining and decomposition at the level of covering numbers, we show how to recover a radical dependence. Examples of applications are given in particular for PWS and swichting regression with linear and kernel-based component functions. [ABSTRACT FROM AUTHOR]

As one of the efficient approaches to deal with big data, divide-and-conquer distributed algorithms, such as the distributed kernel regression, bootstrap, structured perception training algorithms, and so on, are proposed and broadly used in learning systems. Some learning theories have been built to analyze the feasibility, approximation, and convergence bounds of these distributed learning algorithms. However, less work has been studied on the stability of these distributed learning algorithms. In this paper, we discuss the generalization bounds of distributed learning algorithms from the view of algorithmic stability. First, we introduce a definition of uniform distributed stability for distributed algorithms and study the distributed algorithms’ generalization risk bounds. Then, we analyze the stability properties and generalization risk bounds of a kind of regularization-based distributed algorithms. Two generalization distributed risks obtained show that the generalization distributed risk bounds for the difference between their generalization distributed and empirical distributed/leave-one-computer-out risks are closely related to the size of samples $n$ and the amount of working computers $m$ as $\mathcal {O}(m/{n}^{1/2})$. Furthermore, the results in this paper indicate that, for a good generalization regularized distributed kernel algorithm, the regularization parameter $\lambda $ should be adjusted with the change of the term $m/{n}^{1/2}$. These theoretic discoveries provide the useful guidance when deploying the distributed algorithms on practical big data platforms. We explore our theoretic analyses through two simulation experiments. Finally, we discuss some problems about the sufficient amount of working computers, nonequivalence, and generalization for distributed learning. We show that the rules for the computation on one single computer may not always hold for distributed learning. [ABSTRACT FROM AUTHOR]

Although the field of learning automata (LA) has made significant progress in the past four decades, the LA-based methods to tackle problems involving environments with a large number of actions is, in reality, relatively unresolved. The extension of the traditional LA to problems within this domain cannot be easily established when the number of actions is very large. This is because the dimensionality of the action probability vector is correspondingly large, and so, most components of the vector will soon have values that are smaller than the machine accuracy permits, implying that they will never be chosen. This paper presents a solution that extends the continuous pursuit paradigm to such large-actioned problem domains. The beauty of the solution is that it is hierarchical, where all the actions offered by the environment reside as leaves of the hierarchy. Furthermore, at every level, we merely require a two-action LA that automatically resolves the problem of dealing with arbitrarily small action probabilities. In addition, since all the LA invoke the pursuit paradigm, the best action at every level trickles up toward the root. Thus, by invoking the property of the “max” operator, in which the maximum of numerous maxima is the overall maximum, the hierarchy of LA converges to the optimal action. This paper describes the scheme and formally proves its $\epsilon $ -optimal convergence. The results presented here can, rather trivially, be extended for the families of discretized and Bayesian pursuit LA too. This paper also reports extensive experimental results (including for environments having 128 and 256 actions) that demonstrate the power of the scheme and its computational advantages. As far as we know, there are no comparable pursuit-based results in the field of LA. In some cases, the hierarchical continuous pursuit automaton requires less than 18% of the number of iterations than the benchmark $L_{R-I}$ scheme, which is, by all metrics, phenomenal. [ABSTRACT FROM AUTHOR]

This paper deals with the finite-time analysis (FTA) of learning automata (LA), which is a topic for which very little work has been reported in the literature. This is as opposed to the asymptotic steady-state analysis for which there are, probably, scores of papers. As clarified later, unarguably, the FTA of Markov chains, in general, and of LA, in particular, is far more complex than the asymptotic steady-state analysis. Such an FTA provides rigid bounds for the time required for the LA to attain to a given convergence accuracy. We concentrate on the FTA of the Discretized Pursuit Automaton (DPA), which is probably one of the fastest and most accurate reported LA. Although such an analysis was carried out many years ago, we record that the previous work is flawed. More specifically, in all brevity, the flaw lies in the wrongly “derived” monotonic behavior of the LA after a certain number of iterations. Rather, we claim that the property should be invoked is the submartingale property. This renders the proof to be much more involved and deep. In this paper, we rectify the flaw and reestablish the FTA based on such a submartingale phenomenon. More importantly, from the derived analysis, we are able to discover and clarify, for the first time, the underlying dilemma between the DPA’s exploitation and exploration properties. We also nontrivially confirm the existence of the optimal learning rate, which yields a better comprehension of the DPA itself. [ABSTRACT FROM AUTHOR]

This paper studies an adaptive neural network (NN) tracking control method for a class of uncertain nonlinear strict-feedback systems with time-varying full-state constraints. As we all know, the states are inevitably constrained in the actual systems because of the safety and performance factors. The main contributions of this paper are that: 1) in order to ensure that the states do not violate the asymmetric time-varying constraint regions, an adaptive NN controller is constructed by introducing the asymmetric time-varying barrier Lyapunov function (TVBLF) and 2) the amount of the learning parameters is reduced by introducing a TVBLF at each step of the backstepping. Based on the Lyapunov stability analysis, it can be proven that all the signals in the closed-loop system are the semiglobal ultimately uniformly bounded and the time-varying full-state constraints are never violated. Finally, a numerical simulation is given, and the effectiveness of this adaptive control method can be verified. [ABSTRACT FROM AUTHOR]

The time-varying formation problem for multiagent systems (MASs) with stochastic sampling and multiple leaders is studied in this paper, in which communication delays are taken into account. All the agents are divided into the set of the follower group and the set of the leader group. Under the proposed stochastic sampling mechanism for time-varying formation of the MASs with communication delays, the followers are driven to achieve time-varying formation where the center of the formation is the convex combination of the states of the leaders. In the theoretical analysis, sufficient conditions for the MASs achieving time-varying formation in mean square under stochastic sampling with multiple leaders and communication delays are derived. Moreover, some corollaries are also given in this paper. Finally, the theoretical analysis is verified by a given simulation example. [ABSTRACT FROM AUTHOR]

In this paper, the adaptive neural network (NN) tracking control problem is addressed for robot manipulators subject to dead-zone input. The control objective is to design an adaptive NN controller to guarantee the stability of the systems and obtain good performance. Different from the existing results, which used NN to approximate the nonlinearities directly, NNs are employed to identify the originally designed virtual control signals with unknown nonlinear items in this paper. Moreover, a sequence of virtual control signals and real controller are designed. The adaptive backstepping control method and Lyapunov stability theory are used to prove the proposed controller can ensure all the signals in the systems are semiglobally uniformly ultimately bounded, and the output of the systems can track the reference signal closely. Finally, the proposed adaptive control strategy is applied to the Puma 560 robot manipulator to demonstrate its effectiveness. [ABSTRACT FROM AUTHOR]

This paper considers the distributed event-triggered consensus control problem for a network of linear systems subject to bounded uncertainties satisfying the matching condition. Due to the existence of nonidentical uncertainties, the multiagent system studied in this paper is essentially heterogeneous, and the event-triggered consensus problem of which is much more challenging than that of homogeneous linear networks in the existing works. We propose a static nonsmooth event-triggered protocol that includes a nonlinear term to ensure that consensus is achieved and the Zeno behavior is excluded. To avoid the undesirable chattering effect caused by the nonsmooth protocol, we design a static continuous event-based protocol, which can guarantee that the consensus error is ultimately bounded and the upper bound of the consensus error can be made satisfactorily small by choosing properly the design parameters. We also design a continuous adaptive event-triggered protocol that includes time-varying weights into both the control law and the triggering function. Contrary to the event-triggered protocols in the previous related works, the adaptive event-based protocol is fully distributed and scalable, whose design does not require any global information of the network graph. Besides, all the event-triggered protocols in this paper do not need continuous communications among neighboring agents in either control laws’ updating or triggering conditions’ monitoring. [ABSTRACT FROM AUTHOR]

In this paper, we believe that the mixed selectivity of neuron in the top layer encodes distributed information produced from other neurons to offer a significant computational advantage over recognition accuracy. Thus, this paper proposes a hierarchical network framework that the learning behaviors of features combined from hundreds of midlayers. First, a subnetwork neuron, which itself could be constructed by other nodes, is functional as a subspace features extractor. The top layer of a hierarchical network needs subspace features produced by the subnetwork neurons to get rid of factors that are not relevant, but at the same time, to recast the subspace features into a mapping space so that the hierarchical network can be processed to generate more reliable cognition. Second, this paper shows that with noniterative learning strategy, the proposed method has a wider and shallower structure, providing a significant role in generalization performance improvements. Hence, compared with other state-of-the-art methods, multiple channel features with the proposed method could provide a comparable or even better performance, which dramatically boosts the learning speed. Our experimental results show that our platform can provide a much better generalization performance than 55 other state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Video captioning, in essential, is a complex natural process, which is affected by various uncertainties stemming from video content, subjective judgment, and so on. In this paper, we build on the recent progress in using encoder-decoder framework for video captioning and address what we find to be a critical deficiency of the existing methods that most of the decoders propagate deterministic hidden states. Such complex uncertainty cannot be modeled efficiently by the deterministic models. In this paper, we propose a generative approach, referred to as multimodal stochastic recurrent neural networks (MS-RNNs), which models the uncertainty observed in the data using latent stochastic variables. Therefore, MS-RNN can improve the performance of video captioning and generate multiple sentences to describe a video considering different random factors. Specifically, a multimodal long short-term memory (LSTM) is first proposed to interact with both visual and textual features to capture a high-level representation. Then, a backward stochastic LSTM is proposed to support uncertainty propagation by introducing latent variables. Experimental results on the challenging data sets, microsoft video description and microsoft research video-to-text, show that our proposed MS-RNN approach outperforms the state-of-the-art video captioning benchmarks. [ABSTRACT FROM AUTHOR]

Learning under concept drift is a novel and promising research area aiming at designing learning algorithms able to deal with nonstationary data-generating processes. In this research field, most of the literature focuses on learning nonstationary probabilistic frameworks, while some extensions about learning graphs and signals under concept drift exist. For the first time in the literature, this paper addresses the problem of learning discrete-time Markov chains (DTMCs) under concept drift. More specifically, following a hybrid active/passive approach, this paper introduces both a family of change-detection mechanisms (CDMs), differing in the required assumptions and performance, for detecting changes in DTMCs and an adaptive learning algorithm able to deal with DTMCs under concept drift. The effectiveness of both the proposed CDMs and the adaptive learning algorithm has been extensively tested on synthetically generated experiments and real data sets. [ABSTRACT FROM AUTHOR]

This paper determines the weight decay parameter value of a deep convolutional neural network (CNN) that yields a good generalization. To obtain such a CNN in practice, numerical trials with different weight decay values are needed. However, the larger the CNN architecture is, the higher is the computational cost of the trials. To address this problem, this paper formulates an analytical solution for the decay parameter through a proposed objective function in conjunction with Bayesian probability distributions. For computational efficiency, a novel method to approximate this solution is suggested. This method uses a small amount of information in the Hessian matrix. Theoretically, the approximate solution is guaranteed by a provable bound and is obtained by a proposed algorithm, where its time complexity is linear in terms of both the depth and width of the CNN. The bound provides a consistent result for the proposed learning scheme. By reducing the computational cost of determining the decay value, the approximation allows for the fast investigation of a deep CNN (DCNN) which yields a small generalization error. Experimental results show that our assumption verified with different DCNNs is suitable for real-world image data sets. In addition, the proposed method significantly reduces the time cost of learning with setting the weight decay parameter while achieving good classification performances. [ABSTRACT FROM AUTHOR]

This paper deals with the finite-horizon quantized $H_{\infty }$ state estimation problem for a class of discrete time-varying genetic regulatory networks with quantization effects under stochastic communication protocols (SCPs). To better reflect the data-driven flavor of today’s biological research, the network measurements (typically gigabytes in size by high-throughput sequencing technologies) are transmitted to a remote state estimator via two independent communication networks of limited bandwidths. To lighten the communication loads and avoid undesired data collisions, the measurement outputs are quantized and then transmitted under two SCPs introduced to schedule the large-scale data transmissions. The purpose of this paper is to design a time-varying state estimator such that the error dynamics of the state estimation satisfies a prescribed $H_{\infty }$ performance requirement over a finite horizon in the presence of nonlinearities, quantization effects, and SCPs. By utilizing the completing-the-square technique, sufficient conditions are derived to ensure the $H_{\infty }$ estimation performance and the parameters of the state estimator are designed by solving coupled backward recursive Riccati difference equations. A numerical example is given to illustrate the effectiveness of the design scheme of the proposed state estimator. [ABSTRACT FROM AUTHOR]

This paper aims to investigate the fuzzy constrained matrix game (MG) problems using the concepts of recurrent neural networks (RNNs). To the best of our knowledge, this paper is the first in attempting to find a solution for fuzzy game problems using RNN models. For this purpose, a fuzzy game problem is reformulated into a weighting problem. Then, the Karush–Kuhn–Tucker (KKT) optimality conditions are provided for the weighting problem. The KKT conditions are used to propose the RNN model. Moreover, the Lyapunov stability and the global convergence of the RNN model are also confirmed. Finally, three illustrative examples are presented to demonstrate the effectiveness of this approach. The obtained results are compared with the results obtained by the previous approaches for solving fuzzy constrained MG. [ABSTRACT FROM AUTHOR]

In this paper, we introduce the concept of principal paths in data space; we show that this is a well-characterized problem from the point of view of cognition, and that it can lead to salient insights in the analyzed data enabling topological/holistic descriptions. These paths, interestingly, can be interpreted as local principal curves, and in this paper, we suggest that they are analogous to what, in the statistical mechanics realm, are called minimum free-energy paths. Here, we move that concept from physics to data space and compute them in both the original and the kernel space. The algorithm is a regularized version of the well-known $k$ -means clustering algorithm. The regularization parameter is derived via an in-sample model selection process based on the Bayesian evidence maximization. Interestingly, we show that this choice for the regularization parameter consistently leads to the same manifold even when changing the number of clusters. We apply the method to common data sets, dynamical systems, and, in particular, to molecular dynamics trajectories showing the generality, the usefulness of the approach and its superiority with respect to other related approaches. [ABSTRACT FROM AUTHOR]

Organizing multimodal Web pages into hot topics is the core step to grasp trends on the Web. However, the less-constrained social media generate noisy user-generated content, which makes a detected topic be less coherent and less interpretable. In this paper, we address this problem by proposing a coupled Poisson deconvolution to jointly handle topic detection and topic description. For the topic detection, the interestingness of a topic is estimated from the similarities refined by the description of topics; for the topic description, the interestingness of topics is leveraged to describe topics. Two processes cyclically detect interesting topics and generate the multimodal description of topics. This is the innovation of this paper, which just likes killing two birds with one stone. Experiments not only show the significantly improved accuracies for the topic detection but also demonstrate the interpretable descriptions for the topic description on two public data sets. [ABSTRACT FROM AUTHOR]

Unsupervised feature selection is fundamentally important for processing unlabeled high-dimensional data, and several methods have been proposed on this topic. Most existing embedded unsupervised methods just emphasize the data structure in the input space, which may contain large noise. Therefore, they are limited to perceive the discriminative information implied within the low-dimensional manifold. In addition, these methods always involve several parameters to be tuned, which is time-consuming. In this paper, we present a self-tuned discrimination-aware (STDA) approach for unsupervised feature selection. The main contributions of this paper are threefold: 1) it adopts the advantage of discriminant analysis technique to select the valuable features; 2) it learns the local data structure adaptively in the discriminative subspace to alleviate the effect of data noise; and 3) it performs feature selection and clustering simultaneously with an efficient optimization strategy, and saves the additional efforts to tune parameters. Experimental results on a toy data set and various real-world benchmarks justify the effectiveness of STDA on both feature selection and data clustering, and demonstrate its promising performance against the state of the arts. [ABSTRACT FROM AUTHOR]

Prospective authors are requested to submit new, unpublished manuscripts for inclusion in the upcoming event described in this call for papers. [ABSTRACT FROM PUBLISHER]

Describes the above-named upcoming conference event. May include topics to be covered or calls for papers. [ABSTRACT FROM PUBLISHER]

This paper solves the finite-time switching control issue for the nonstrict-feedback nonlinear switched systems. The controlled plants contain immeasurable states, arbitrarily switchings, and the unknown functions which are constructed with the whole states. Neural network is used to simulate the uncertain systems and a filter-based state observer is designed to estimate the immeasurable states in this paper, respectively. Based on the backstepping recursive technique and the common Lyapunov function method, a finite-time switching control method is presented. Due to the developed finite-time control strategy, the closed-loop signals can be ensured to be bounded under arbitrarily switchings, and the outputs of systems can quickly track the desired reference signals in finite time. The effectiveness of the proposed method is given through its application to a mass-spring-damper system. [ABSTRACT FROM AUTHOR]

Memristive crossbars have become a popular means for realizing unsupervised and supervised learning techniques. In previous neuromorphic architectures with leaky integrate-and-fire neurons, the crossbar itself has been separated from the neuron capacitors to preserve mathematical rigor. In this paper, we sought to design a simplified sparse coding circuit without this restriction, resulting in a fast circuit that approximated a sparse coding operation at a minimal loss in accuracy. We showed that connecting the neurons directly to the crossbar resulted in a more energy-efficient sparse coding architecture and alleviated the need to prenormalize receptive fields. This paper provides derivations for the design of such a network, named the simple spiking locally competitive algorithm, as well as CMOS designs and results on the CIFAR and MNIST data sets. Compared to a nonspiking, nonapproximate model which scored 33% on CIFAR-10 with a single-layer classifier, this hardware scored 32% accuracy. When used with a state-of-the-art deep learning classifier, the nonspiking model achieved 82% and our simplified, spiking model achieved 80% while compressing the input data by 92%. Compared to a previously proposed spiking model, our proposed hardware consumed 99% less energy to do the same work at 21 $\times $ the throughput. Accuracy held out with online learning to a write variance of 3%, suitable for the often reported 4-bit resolution required for neuromorphic algorithms, with offline learning to a write variance of 27%, and with read variance to 40%. The proposed architecture’s excellent accuracy, throughput, and significantly lower energy usage demonstrate the utility of our innovations. [ABSTRACT FROM AUTHOR]

The class imbalance issue has been a persistent problem in machine learning that hinders the accurate predictive analysis of data in many real-world applications. The class imbalance problem exists when the number of instances present in a class (or classes) is significantly fewer than the number of instances belonging to another class (or classes). Sufficiently recognizing the minority class during classification is a problem as most algorithms employed to learn from data input are biased toward the majority class. The underlying issue is made more complex with the presence of data difficult factors embedded in such data input. This paper presents a novel and effective ensemble-based method for dealing with the class imbalance problem. This paper is motivated by the idea of moving the oversampling from the data level to the algorithm level, instead of increasing the minority instances in the data sets, the algorithms in this paper aims to “oversample the classification ensemble” by increasing the number of classifiers that represent the minority class in the ensemble, i.e., random forest. The proposed biased random forest algorithm employs the nearest neighbor algorithm to identify the critical areas in a given data set. The standard random forest is then fed with more random trees generated based on the critical areas. The results show that the proposed algorithm is very effective in dealing with the class imbalance problem. [ABSTRACT FROM AUTHOR]

This paper is concerned with the global nonfragile Mittag–Leffler synchronization and the global synchronization in finite time for fractional-order discontinuous neural networks, where activation functions are discontinuous at 0, or modeled as a local Hölder functions with the nonlinear growth property in a neighborhood of 0. First, two lemmas concerned with the convergence with respect to an absolutely continuous function are developed. Second, a new property, which introduces an inequality of the fractional derivative for the variable upper limit integral with respect to the nonsmooth integrable function, is presented and applied in the synchronization results’ analysis. In addition, under the fractional Filippov differential inclusion framework, by utilizing the Lur’e Postnikov-type Lyapunov functional, nonsmooth analysis method, and the convergence properties developed in this paper, the synchronization conditions are derived in the form of linear matrix inequalities. Moreover, the upper bound of the setting time for the global nonfragile synchronization in finite time is calculated accurately. Finally, two illustrations are presented to verify the correctness of the theoretical results. [ABSTRACT FROM AUTHOR]

The low-voltage low-power sinh-domain (SD) implementations of integer- and fractional-order FitzHugh–Nagumo (FHN) neuron model have been introduced in this paper. Besides, the effect of fractional-orders on the external excitation current and dynamics of the neuron has been examined in this paper. The proposed SD designs of FHN neuron model have the benefits of: 1) low-voltage operation; 2) integrability, due to resistor-less design and the employment of only grounded components; 3) electronic tunability of performance parameters; and 4) low-power implementation due to the inherent properties of SD technique. HSPICE simulator tool and Taiwan Semiconductor Manufacturing Company, Hsinchu, Taiwan 130-nm CMOS process was used to evaluate and verify the correct functioning of the model. In addition, to experimentally verify the operation of the proposed fractional-order FHN neuron model, field-programmable analog array (FPAA) implementation of the model has been presented, and the proper functioning of the model has been verified. To the best of the authors’ knowledge, this is the first paper that describes the electronic realization of the fractional-order FHN neuron model. In addition, it is the first time that the FPAA implementation of any fractional-order neuron model has been presented. [ABSTRACT FROM AUTHOR]

This paper provides the stability analysis for a model-free action-dependent heuristic dynamic programing (HDP) approach with an eligibility trace long-term prediction parameter ($\lambda $). HDP($\lambda $) learns from more than one future reward. Eligibility traces have long been popular in Q-learning. This paper proves and demonstrates that they are worthwhile to use with HDP. In this paper, we prove its uniformly ultimately bounded (UUB) property under certain conditions. Previous works present a UUB proof for traditional HDP [HDP($\lambda =0$)], but we extend the proof with the $\lambda $ parameter. By using Lyapunov stability, we demonstrate the boundedness of the estimated error for the critic and actor neural networks as well as learning rate parameters. Three case studies demonstrate the effectiveness of HDP($\lambda $). The trajectories of the internal reinforcement signal nonlinear system are considered as the first case. We compare the results with the performance of HDP and traditional temporal difference [TD($\lambda $)] with different $\lambda $ values. The second case study is a single-link inverted pendulum. We investigate the performance of the inverted pendulum by comparing HDP($\lambda $) with regular HDP, with different levels of noise. The third case study is a 3-D maze navigation benchmark, which is compared with state action reward state action, Q($\lambda $), HDP, and HDP($\lambda $). All these simulation results illustrate that HDP($\lambda $) has a competitive performance; thus this contribution is not only UUB but also useful in comparison with traditional HDP. [ABSTRACT FROM AUTHOR]

This paper presents an improved method for reducing high-order dynamical system models via clustering. Agglomerative hierarchical clustering based on performance evaluation (HC-PE) is introduced for model order reduction. This method computes the reduced order denominator of the transfer function model by clustering system poles in a hierarchical dendrogram. The base layer represents an $n{\textrm {th}}$ order system, which is used to calculate each successive layer to reduce the model order until finally reaching a second-order system. HC-PE uses a mean-squared error (MSE) in every reduced order, which modifies the pole placement process. The coefficients for the numerator of the reduced model are calculated by using the Padé approximation (PA) or alternatively a genetic algorithm (GA). Several numerical examples of reducing techniques are taken from the literature to compare with HC-PE. Two classes of results are shown in this paper. The first sets are single-input single-output models that range from simple models to 48th order systems. The second sets of experiments are with a multi-input multioutput model. We demonstrate the best performance for HC-PE through minimum MSEs compared with other methods. Furthermore, the robustness of HC-PE combined with PA or GA is confirmed by evaluating the third-order reduced model for the triple-link inverted pendulum model by adding a disturbance impulse signal and by changing model parameters. The relevant stability proofs are provided in Appendixes A and B in the supplementary material. HC-PE with PA slightly outperforms its performance with GA, but both approaches are attractive alternatives to other published methods. [ABSTRACT FROM AUTHOR]

This paper studies the distributed average tracking (DAT) problem for multiple reference signals described by the second-order nonlinear dynamical systems. Leveraging the state-dependent gain design and the adaptive control approaches, a couple of DAT algorithms are developed in this paper, which are named finite-time and adaptive-gain DAT algorithms. Based on the finite-time one, the states of the physical agents in this paper can track the average of the time-varying reference signals within a finite settling time. Furthermore, the finite settling time is also estimated by considering a well-designed Lyapunov function in this paper. Compared with asymptotical DAT algorithms, the proposed finite-time algorithm not only solve finite-time DAT problems but also ensure states of physical agents to achieve an accurate average of the multiple signals. Then, an adaptive-gain DAT algorithm is designed. Based on the adaptive-gain one, the DAT problem is solved without global information. Thus, it is fully distributed. Finally, numerical simulations show the effectiveness of the theoretical results. [ABSTRACT FROM AUTHOR]

This paper proposes a Bayesian nonparametric framework for clustering axially symmetric data. Our approach is based on a Dirichlet processes mixture model with Watson distributions, which can also be considered as the infinite Watson mixture model. In this paper, first, we extend the finite Watson mixture model into its infinite counterpart based on the framework of truncated Dirichlet process mixture model with a stick-breaking representation. Second, we propose a coordinate ascent mean-field variational inference algorithm that can effectively learn the parameters of our model with closed-form solutions; Third, to cope with a massive data set, we develop a stochastic variational inference algorithm to learn the proposed model through the method of stochastic gradient ascent; Finally, the proposed nonparametric Bayesian model is evaluated through simulated axially symmetric data sets and a real-world application, namely, gene expression data clustering. [ABSTRACT FROM AUTHOR]

A growing number of applications, e.g., video surveillance and medical image analysis, require training recognition systems from large amounts of weakly annotated data, while some targeted interactions with a domain expert are allowed to improve the training process. In such cases, active learning (AL) can reduce labeling costs for training a classifier by querying the expert to provide the labels of most informative instances. This paper focuses on AL methods for instance classification problems in multiple instance learning (MIL), where data are arranged into sets, called bags, which are weakly labeled. Most AL methods focus on single-instance learning problems. These methods are not suitable for MIL problems because they cannot account for the bag structure of data. In this paper, new methods for bag-level aggregation of instance informativeness are proposed for multiple instance AL (MIAL). The aggregated informativeness method identifies the most informative instances based on classifier uncertainty and queries bags incorporating the most information. The other proposed method, called cluster-based aggregative sampling, clusters data hierarchically in the instance space. The informativeness of instances is assessed by considering bag labels, inferred instance labels, and the proportion of labels that remain to be discovered in clusters. Both proposed methods significantly outperform reference methods in extensive experiments using benchmark data from several application domains. Results indicate that using an appropriate strategy to address MIAL problems yields a significant reduction in the number of queries needed to achieve the same level of performance as single-instance AL methods. [ABSTRACT FROM AUTHOR]

This paper studies the compound learning control of disturbed uncertain strict-feedback systems. The design is using the dynamic surface control equipped with a novel learning scheme. This paper integrates the recently developed online recorded data-based neural learning with the nonlinear disturbance observer (DOB) to achieve good “understanding” of the system uncertainty including unknown dynamics and time-varying disturbance. With the proposed method to show how the neural networks and DOB are cooperating with each other, one indicator is constructed and included into the update law. The closed-loop system stability analysis is rigorously presented. Different kinds of disturbances are considered in a third-order system as simulation examples and the results confirm that the proposed method achieves higher tracking accuracy while the compound estimation is much more precise. The design is applied to the flexible hypersonic flight dynamics and a better tracking performance is obtained. [ABSTRACT FROM AUTHOR]

This paper presents a new time-varying long-term Synaptic Efficacy Function-based leaky-integrate-and-fire neuRON model, referred to as SEFRON and its supervised learning rule for pattern classification problems. The time-varying synaptic efficacy function is represented by a sum of amplitude modulated Gaussian distribution functions located at different times. For a given pattern, the SEFRON’s learning rule determines the changes in the amplitudes of weights at selected presynaptic spike times by minimizing a new error function reflecting the differences between the desired and actual postsynaptic firing times. Similar to the gamma-aminobutyric acid-switch phenomenon observed in a biological neuron that switches between excitatory and inhibitory postsynaptic potentials based on the physiological needs, the time-varying synapse model proposed in this paper allows the synaptic efficacy (weight) to switch signs in a continuous manner. The computational power and the functioning of SEFRON are first illustrated using a binary pattern classification problem. The detailed performance comparisons of a single SEFRON classifier with other spiking neural networks (SNNs) are also presented using four benchmark data sets from the UCI machine learning repository. The results clearly indicate that a single SEFRON provides a similar generalization performance compared to other SNNs with multiple layers and multiple neurons. [ABSTRACT FROM AUTHOR]