Search

In this paper, we first address the dynamics of the elegant multivalued quaternionic Hopfield neural network (MV-QHNN) proposed by Minemoto et al. Contrary to what was expected, we show that the MV-QHNN, as well as one of its variation, does not always come to rest at an equilibrium state under the usual conditions. In fact, we provide simple examples in which the network yields a periodic sequence of quaternionic state vectors. Afterward, we turn our attention to the continuous-valued quaternionic Hopfield neural network (CV-QHNN), which can be derived from the MV-QHNN by means of a limit process. The CV-QHNN can be implemented more easily than the MV-QHNN model. Furthermore, the asynchronous CV-QHNN always settles down into an equilibrium state under the usual conditions. Theoretical issues are all illustrated by examples in this paper. [ABSTRACT FROM AUTHOR]

The stability property of delayed neural networks (NNs) along the whole delay axis is studied in this paper. Such a complete stability problem with respect to the delay parameter has not been addressed in the community of NNs. Most of the existing studies focus on the stability interval of delay starting from zero and are not applicable for the complete stability problem. In this paper, we will present some examples to show that there are various types of stability intervals for NNs, demonstrating the necessity of the complete stability analysis. We will adopt a frequency-sweeping approach to study delayed NNs in this paper. As a result, the complete stability problem with respect to delay for NNs can be systematically solved. The approach is applicable in the general case and simple to implement. Finally, some representative examples illustrate the approach. [ABSTRACT FROM AUTHOR]

Neural networks (NNs) in the stochastic environment were widely modeled as stochastic differential equations, which were driven by white noise, such as Brown or Wiener process in the existing papers. However, they are not necessarily the best models to describe dynamic characters of NNs disturbed by nonwhite noise in some specific situations. In this paper, general noise disturbance, which may be nonwhite, is introduced to NNs. Since NNs with nonwhite noise cannot be described by Itô integral equation, a novel modeling method of stochastic NNs is utilized. By a framework in light of random field approach and Lyapunov theory, the global asymptotic stability and stabilization in probability or in the mean square of NNs with general noise are analyzed, respectively. Criteria for the concerned systems based on linear matrix inequality are proposed. Some examples are given to illustrate the effectiveness of the obtained results. [ABSTRACT FROM PUBLISHER]

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 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]

Approximate dynamic programming (ADP) and reinforcement learning (RL) have emerged as important tools in the design of optimal and adaptive control systems. Most of the existing RL and ADP methods make use of full-state feedback, a requirement that is often difficult to satisfy in practical applications. As a result, output feedback methods are more desirable as they relax this requirement. In this paper, we present a new output feedback-based Q-learning approach to solving the linear quadratic regulation (LQR) control problem for discrete-time systems. The proposed scheme is completely online in nature and works without requiring the system dynamics information. More specifically, a new representation of the LQR Q-function is developed in terms of the input–output data. Based on this new Q-function representation, output feedback LQR controllers are designed. We present two output feedback iterative Q-learning algorithms based on the policy iteration and the value iteration methods. This scheme has the advantage that it does not incur any excitation noise bias, and therefore, the need of using discounted cost functions is circumvented, which in turn ensures closed-loop stability. It is shown that the proposed algorithms converge to the solution of the LQR Riccati equation. A comprehensive simulation study is carried out, which illustrates the proposed scheme. [ABSTRACT FROM AUTHOR]

Artificial neural networks (ANNs) have traditionally been seen as black-box models, because, although they are able to find “hidden” relations between inputs and outputs with a high approximation capacity, their structure seldom provides any insights on the structure of the functions being approximated. Several research papers have tried to debunk the black-box nature of ANNs, since it limits the potential use of ANNs in many research areas. This paper is framed in this context and proposes a methodology to determine the individual and collective effects of the input variables on the outputs for classification problems based on the ANOVA-functional decomposition. The method is applied after the training phase of the ANN and allows researchers to rank the input variables according to their importance in the variance of the ANN output. The computation of the sensitivity indices for product unit neural networks is straightforward as those indices can be calculated analytically by evaluating the integrals in the ANOVA decomposition. Unfortunately, the sensitivity indices associated with ANNs based on sigmoidal basis functions or radial basis functions cannot be calculated analytically. In this paper, the indices for those kinds of ANNs are proposed to be estimated by the (quasi-) Monte Carlo method. [ABSTRACT FROM PUBLISHER]

In this paper, we propose a new approach to implementing hierarchical graph neuron (HGN), an architecture for memorizing patterns of generic sensor stimuli, through the use of vector symbolic architectures. The adoption of a vector symbolic representation ensures a single-layer design while retaining the existing performance characteristics of HGN. This approach significantly improves the noise resistance of the HGN architecture, and enables a linear (with respect to the number of stored entries) time search for an arbitrary subpattern. [ABSTRACT FROM PUBLISHER]

This paper describes the learning and control capabilities of a biologically constrained bottom-up model of the mammalian cerebellum. Results are presented from six tasks: 1) eyelid conditioning; 2) pendulum balancing; 3) proportional–integral–derivative control; 4) robot balancing; 5) pattern recognition; and 6) MNIST handwritten digit recognition. These tasks span several paradigms of machine learning, including supervised learning, reinforcement learning, control, and pattern recognition. Results over these six domains indicate that the cerebellar simulation is capable of robustly identifying static input patterns even when randomized across the sensory apparatus. This capability allows the simulated cerebellum to perform several different supervised learning and control tasks. On the other hand, both reinforcement learning and temporal pattern recognition prove problematic due to the delayed nature of error signals and the simulator’s inability to solve the credit assignment problem. These results are consistent with previous findings which hypothesize that in the human brain, the basal ganglia is responsible for reinforcement learning, while the cerebellum handles supervised learning. [ABSTRACT FROM PUBLISHER]

It has been shown that brain-like self-repair can arise from the interactions between neurons and astrocytes where endocannabinoids are synthesized and released from active neurons. This retrograde messenger feeds back to local synapses directly and indirectly to distant synapses via astrocytes. This direct/indirect feedback of the endocannabinoid retrograde messenger results in the modulation of the probability of release (PR) at synaptic sites. When synapses fail, there is a corresponding falloff in the firing activity of the associated neurons, and hence the strength of the direct feedback messenger diminishes. This triggers an increase in PR of healthy synapses, due to the indirect messenger from other active neurons, which is the catalyst for the repair process. In this paper, the repair process is implemented by developing a new learning rule that captures the spike-timing-dependent plasticity and Bienenstock, Cooper, and Munro learning rules. The rule is activated by the increase in PR and results in a potentiation of the weight values, which reestablishes the firing activity of neurons. In addition, this self-repairing mechanism is extended to network-level repair where astrocyte to astrocyte communications are implemented using a linear gap junction model. This facilitates the implementation of an astroglial syncytium involving multiple astrocytes, which relays the indirect feedback messenger to distant neurons: each astrocyte is bidirectionally coupled to neurons. A detailed and comprehensive set of results with analysis is presented demonstrating repair at both cellular and network levels. [ABSTRACT FROM PUBLISHER]

In this paper, an adaptive dynamic programming-based near optimal boundary controller is developed for partial differential equations (PDEs) modeled by the uncertain Burgers’ equation under Neumann boundary condition in 2-D. Initially, Hamilton–Jacobi–Bellman equation is derived in infinite-dimensional space. Subsequently, a novel neural network (NN) identifier is introduced to approximate the nonlinear dynamics in the 2-D PDE. The optimal control input is derived by online estimation of the value function through an additional NN-based forward-in-time estimation and approximated dynamic model. Novel update laws are developed for estimation of the identifier and value function online. The designed control policy can be applied using a finite number of actuators at the boundaries. Local ultimate boundedness of the closed-loop system is studied in detail using Lyapunov theory. Simulation results confirm the optimizing performance of the proposed controller on an unstable 2-D Burgers’ equation. [ABSTRACT FROM AUTHOR]

In this paper, a differential neural network (DNN) implemented as a robust observer estimates the dynamics of perturbed uncertain nonlinear systems affected by exogenous unknown inputs. In the first stage, the identification error converges into a neighborhood around the origin. Then, the second-order sliding mode supertwisting algorithm implemented as a robust exact differentiator reconstructed the unknown inputs. The approach proposed in this paper can be applied in the case of full access to the state vector (identification problem) and in the case of partial access to the state vector (estimation problem). In the second case, the nonlinear system under study must have well-defined full relative degree with respect to the unknown input. Numerical examples showed the effectiveness of the proposed algorithm. The first example tested the DNN working as an identifier into a mathematical model describing the dynamics of a spatial minisatellite. The second example (with a DNN implemented as an observer) tested the methodology of this paper over a single link flexible robot manipulator represented in a canonical (Brunovsky) form. In both examples, the mathematical models served as data generators in the testing of the neural networks. Even when not exact mathematical description of both models was used in the input estimation, the accuracy obtained with the DNN is comparable with the case of applying a high-order differentiator with complete knowledge of the plant. [ABSTRACT FROM AUTHOR]

This paper proposes a novel data-driven control approach to address the problem of adaptive optimal tracking for a class of nonlinear systems taking the strict-feedback form. Adaptive dynamic programming (ADP) and nonlinear output regulation theories are integrated for the first time to compute an adaptive near-optimal tracker without any a priori knowledge of the system dynamics. Fundamentally different from adaptive optimal stabilization problems, the solution to a Hamilton-Jacobi–Bellman (HJB) equation, not necessarily a positive definite function, cannot be approximated through the existing iterative methods. This paper proposes a novel policy iteration technique for solving positive semidefinite HJB equations with rigorous convergence analysis. A two-phase data-driven learning method is developed and implemented online by ADP. The efficacy of the proposed adaptive optimal tracking control methodology is demonstrated via a Van der Pol oscillator with time-varying exogenous signals. [ABSTRACT FROM AUTHOR]

High-dimensional data present in the real world is often corrupted by noise and gross outliers. Principal component analysis (PCA) fails to learn the true low-dimensional subspace in such cases. This is the reason why robust versions of PCA, which put a penalty on arbitrarily large outlying entries, are preferred to perform dimension reduction. In this paper, we argue that it is necessary to study the presence of outliers not only in the observed data matrix but also in the orthogonal complement subspace of the authentic principal subspace. In fact, the latter can seriously skew the estimation of the principal components. A reinforced robustification of principal component pursuit is designed in order to cater to the problem of finding out both types of outliers and eliminate their influence on the final subspace estimation. Simulation results under different design situations clearly show the superiority of our proposed method as compared with other popular implementations of robust PCA. This paper also showcases possible applications of our method in critically tough scenarios of face recognition and video background subtraction. Along with approximating a usable low-dimensional subspace from real-world data sets, the technique can capture semantically meaningful outliers. [ABSTRACT FROM AUTHOR]

The centers and radii of radial basis functions (RBFs) greatly affect the approximation capability of RBF networks (RBFNs). Traditional statistics-based approaches are widely used, but they may lack adaptivity to different data structures. Quantum clustering (QC), derived from quantum mechanics and the Schrödinger equation, demonstrates excellent capability in finding the structure and conformity toward data distribution. In this paper, a novel neural networks model called quantum local potential function networks (QLPFNs) is proposed. The QLPFN inherits the outstanding properties of QC by constructing the waves and the potential functions, and the level of data concentration can be discovered to obtain the inherent structures of the given data set. The local potential functions form the basic components of the QLPFN structure, which are automatically generated from the subsets of training data following specific subspace division procedures. Therefore, the QLPFN model in fact incorporates the level of data concentration as a computation technique, which is different from the classical RBFN model that exhibits radial symmetry toward specific centers. Some application examples are given in this paper to show the effectiveness of the QLPFN model. [ABSTRACT FROM AUTHOR]

This paper develops and validates a comprehensive and universally applicable computational concept for solving nonlinear differential equations (NDEs) through a neurocomputing concept based on cellular neural networks (CNNs). High-precision, stability, convergence, and lowest-possible memory requirements are ensured by the CNN processor architecture. A significant challenge solved in this paper is that all these cited computing features are ensured in all system-states (regular or chaotic ones) and in all bifurcation conditions that may be experienced by NDEs.One particular quintessence of this paper is to develop and demonstrate a solver concept that shows and ensures that CNN processors (realized either in hardware or in software) are universal solvers of NDE models. The solving logic or algorithm of given NDEs (possible examples are: Duffing, Mathieu, Van der Pol, Jerk, Chua, Rössler, Lorenz, Burgers, and the transport equations) through a CNN processor system is provided by a set of templates that are computed by our comprehensive templates calculation technique that we call nonlinear adaptive optimization. This paper is therefore a significant contribution and represents a cutting-edge real-time computational engineering approach, especially while considering the various scientific and engineering applications of this ultrafast, energy-and-memory-efficient, and high-precise NDE solver concept. For illustration purposes, three NDE models are demonstratively solved, and related CNN templates are derived and used: the periodically excited Duffing equation, the Mathieu equation, and the transport equation. [ABSTRACT FROM PUBLISHER]

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]

A typical recurrent neural network called zeroing neural network (ZNN) was developed for time-varying problem-solving in a previous study. Many applications result in time-varying linear equation and inequality systems that should be solved in real time. This paper provides a ZNN model for determining the solution of time-varying linear equation and inequality systems. By introducing a nonnegative slack variable, the time-varying linear equation and inequality systems are transformed into a mixed nonlinear system. The ZNN model is established via the definition of an indefinite error function and the usage of an exponential decay formula. Theoretical results indicate the convergence property of the proposed ZNN model. Comparative simulation results prove the ZNN effectiveness and superiority for time-varying linear equation and inequality systems. Furthermore, the proposed ZNN model is employed to robot manipulators, thus showing the ZNN applicability. [ABSTRACT FROM AUTHOR]

Due to the lack of enough generalization in the state space, common methods of reinforcement learning suffer from slow learning speed, especially in the early learning trials. This paper introduces a model-based method in discrete state spaces for increasing the learning speed in terms of required experiences (but not required computation time) by exploiting generalization in the experiences of the subspaces. A subspace is formed by choosing a subset of features in the original state representation. Generalization and faster learning in a subspace are due to many-to-one mapping of experiences from the state space to each state in the subspace. Nevertheless, due to inherent perceptual aliasing (PA) in the subspaces, the policy suggested by each subspace does not generally converge to the optimal policy. Our approach, called model-based learning with subspaces (MoBLeSs), calculates the confidence intervals of the estimated $Q$ -values in the state space and in the subspaces. These confidence intervals are used in the decision-making, such that the agent benefits the most from the possible generalization while avoiding from the detriment of the PA in the subspaces. The convergence of MoBLeS to the optimal policy is theoretically investigated. In addition, we show through several experiments that MoBLeS improves the learning speed in the early trials. [ABSTRACT FROM AUTHOR]

It is well known that active learning can simultaneously improve the quality of the classification model and decrease the complexity of training instances. However, several previous studies have indicated that the performance of active learning is easily disrupted by an imbalanced data distribution. Some existing imbalanced active learning approaches also suffer from either low performance or high time consumption. To address these problems, this paper describes an efficient solution based on the extreme learning machine (ELM) classification model, called active online-weighted ELM (AOW-ELM). The main contributions of this paper include: 1) the reasons why active learning can be disrupted by an imbalanced instance distribution and its influencing factors are discussed in detail; 2) the hierarchical clustering technique is adopted to select initially labeled instances in order to avoid the missed cluster effect and cold start phenomenon as much as possible; 3) the weighted ELM (WELM) is selected as the base classifier to guarantee the impartiality of instance selection in the procedure of active learning, and an efficient online updated mode of WELM is deduced in theory; and 4) an early stopping criterion that is similar to but more flexible than the margin exhaustion criterion is presented. The experimental results on 32 binary-class data sets with different imbalance ratios demonstrate that the proposed AOW-ELM algorithm is more effective and efficient than several state-of-the-art active learning algorithms that are specifically designed for the class imbalance scenario. [ABSTRACT FROM AUTHOR]

In this paper, the receding horizon near-optimal tracking control problem about a class of continuous-time nonlinear systems with fully unknown dynamics is considered. The main challenges of this problem lie in two aspects: 1) most existing systems only restrict their considerations to the state feedback part while the input channel parameters are assumed to be known. This paper considers fully unknown system dynamics in both the state feedback channel and the input channel and 2) the optimal control of nonlinear systems requires the solution of nonlinear Hamilton–Jacobi–Bellman equations. Up to date, there are no systematic approaches in the existing literature to solve it accurately. A novel model-free adaptive near-optimal control method is proposed to solve this problem via utilizing the Taylor expansion-based problem relaxation, the universal approximation property of sigmoid neural networks, and the concept of sliding mode control. By making approximation for the performance index, it is first relaxed to a quadratic program, and then, a linear algebraic equation with unknown terms. An auxiliary system is designed to reconstruct the input-to-output property of the control systems with unknown dynamics, so as to tackle the difficulty caused by the unknown terms. Then, by considering the property of the sliding-mode surface, an explicit adaptive near-optimal control law is derived from the linear algebraic equation. Theoretical analysis shows that the auxiliary system is convergent, the resultant closed-loop system is asymptotically stable, and the performance index asymptomatically converges to optimal. An illustrative example and experimental results are presented, which substantiate the efficacy of the proposed method and verify the theoretical results. [ABSTRACT FROM AUTHOR]

This paper proposes a Bayesian nonparametric regression model of panel data for sequential pattern classification. The proposed method provides a flexible and parsimonious model that allows both time-independent spatial variables and time-dependent exogenous variables to be predictors. Not only this method improves the accuracy of parameter estimation for limited data, but also it facilitates model interpretation by identifying statistically significant predictors with hypothesis testing. Moreover, as the data length approaches infinity, posterior consistency of the model is guaranteed for general data-generating processes under regular conditions. The resulting model of panel data can also be used for sequential classification. The proposed method has been tested by numerical simulation, then validated on an econometric public data set, and subsequently validated for detection of combustion instabilities with experimental data that have been generated in a laboratory environment. [ABSTRACT FROM AUTHOR]

This paper presents a recurrent neural network (RNN) for computing the Drazin inverse of a real matrix in real time. This recurrent neural network (RNN) is composed of $n$ independent parts (subnetworks), where $n$ is the order of the input matrix. These subnetworks can operate concurrently, so parallel and distributed processing can be achieved. In this way, the computational advantages over the existing sequential algorithms can be attained in real-time applications. The RNN defined in this paper is convenient for an implementation in an electronic circuit. The number of neurons in the neural network is the same as the number of elements in the output matrix, which represents the Drazin inverse. The difference between the proposed RNN and the existing ones for the Drazin inverse computation lies in their network architecture and dynamics. The conditions that ensure the stability of the defined RNN as well as its convergence toward the Drazin inverse are considered. In addition, illustrative examples and examples of application to the practical engineering problems are discussed to show the efficacy of the proposed neural network. [ABSTRACT FROM PUBLISHER]

In this paper, we deal with the problem of inferring causal relations for multidimensional data. Based on the postulate that the distribution of the cause and the conditional distribution of the effect given cause are generated independently, we show that the covariance matrix of the mean embedding of the cause in reproducing kernel Hilbert space (RKHS) is free independent with the covariance matrix of the conditional embedding of the effect given cause. This, called freeness condition, induces a cause–effect asymmetry that a designed measurement is 0 in the causal direction but smaller than 0 in the anticausal direction, and it uncovers the causal direction. One important novel aspect of this paper is that we interpret the independence as a freeness condition between covariance matrices of RKHS distribution embeddings, and it has a wide applicability. We show that our freeness condition-based inference method succeeds in scenarios like additive noise cases, where other methods fail, by theoretical analysis and experimental results. [ABSTRACT FROM AUTHOR]

Typical dimensionality reduction (DR) methods are data-oriented, focusing on directly reducing the number of random variables (or features) while retaining the maximal variations in the high-dimensional data. Targeting unsupervised situations, this paper aims to address the problem from a novel perspective and considers model-oriented DR in parameter spaces of binary multivariate distributions. Specifically, we propose a general parameter reduction criterion, called confident-information-first (CIF) principle, to maximally preserve confident parameters and rule out less confident ones. Formally, the confidence of each parameter can be assessed by its contribution to the expected Fisher information distance within a geometric manifold over the neighborhood of the underlying real distribution. Then, we demonstrate two implementations of CIF in different scenarios. First, when there are no observed samples, we revisit the Boltzmann machines (BMs) from a model selection perspective and theoretically show that both the fully visible BM and the BM with hidden units can be derived from the general binary multivariate distribution using the CIF principle. This finding would help us uncover and formalize the essential parts of the target density that BM aims to capture and the nonessential parts that BM should discard. Second, when there exist observed samples, we apply CIF to the model selection for BM, which is in turn made adaptive to the observed samples. The sample-specific CIF is a heuristic method to decide the priority order of parameters, which can improve the search efficiency without degrading the quality of model selection results as shown in a series of density estimation experiments. [ABSTRACT FROM AUTHOR]

In this paper, neurodynamic programming-based output feedback boundary control of distributed parameter systems governed by uncertain coupled semilinear parabolic partial differential equations (PDEs) under Neumann or Dirichlet boundary control conditions is introduced. First, Hamilton-Jacobi–Bellman (HJB) equation is formulated in the original PDE domain and the optimal control policy is derived using the value functional as the solution of the HJB equation. Subsequently, a novel observer is developed to estimate the system states given the uncertain nonlinearity in PDE dynamics and measured outputs. Consequently, the suboptimal boundary control policy is obtained by forward-in-time estimation of the value functional using a neural network (NN)-based online approximator and estimated state vector obtained from the NN observer. Novel adaptive tuning laws in continuous time are proposed for learning the value functional online to satisfy the HJB equation along system trajectories while ensuring the closed-loop stability. Local uniformly ultimate boundedness of the closed-loop system is verified by using Lyapunov theory. The performance of the proposed controller is verified via simulation on an unstable coupled diffusion reaction process. [ABSTRACT FROM PUBLISHER]

This paper studies the effects of uniform input noise and Gaussian input noise on the dual neural network-based $k$ WTA (DNN- $k$ WTA) model. We show that the state of the network (under either uniform input noise or Gaussian input noise) converges to one of the equilibrium points. We then derive a formula to check if the network produce correct outputs or not. Furthermore, for the uniformly distributed inputs, two lower bounds (one for each type of input noise) on the probability that the network produces the correct outputs are presented. Besides, when the minimum separation amongst inputs is given, we derive the condition for the network producing the correct outputs. Finally, experimental results are presented to verify our theoretical results. Since random drift in the comparators can be considered as input noise, our results can be applied to the random drift situation. [ABSTRACT FROM AUTHOR]

Quantum-inspired computing is an emerging research area, which has significantly improved the capabilities of conventional algorithms. In general, quantum-inspired hopfield associative memory (QHAM) has demonstrated quantum information processing in neural structures. This has resulted in an exponential increase in storage capacity while explaining the extensive memory, and it has the potential to illustrate the dynamics of neurons in the human brain when viewed from quantum mechanics perspective although the application of QHAM is limited as an autoassociation. We introduce a quantum-inspired multidirectional associative memory (QMAM) with a one-shot learning model, and QMAM with a self-convergent iterative learning model (IQMAM) based on QHAM in this paper. The self-convergent iterative learning enables the network to progressively develop a resonance state, from inputs to outputs. The simulation experiments demonstrate the advantages of QMAM and IQMAM, especially the stability to recall reliability. [ABSTRACT FROM AUTHOR]

This paper studies the problem of exactly identifying the structure of a probabilistic Boolean network (PBN) from a given set of samples, where PBNs are probabilistic extensions of Boolean networks. Cheng et al. studied the problem while focusing on PBNs consisting of pairs of AND/OR functions. This paper considers PBNs consisting of Boolean threshold functions while focusing on those threshold functions that have unit coefficients. The treatment of Boolean threshold functions, and triplets and n -tuplets of such functions, necessitates a deepening of the theoretical analyses. It is shown that wide classes of PBNs with such threshold functions can be exactly identified from samples under reasonable constraints, which include: 1) PBNs in which any number of threshold functions can be assigned provided that all have the same number of input variables and 2) PBNs consisting of pairs of threshold functions with different numbers of input variables. It is also shown that the problem of deciding the equivalence of two Boolean threshold functions is solvable in pseudopolynomial time but remains co-NP complete. [ABSTRACT FROM AUTHOR]

This paper addresses the problem of state estimation for delayed genetic regulatory networks (DGRNs) with reaction-diffusion terms using Dirichlet boundary conditions. The nonlinear regulation function of DGRNs is assumed to exhibit the Hill form. The aim of this paper is to design a state observer to estimate the concentrations of mRNAs and proteins via available measurement techniques. By introducing novel integral terms into the Lyapunov-Krasovskii functional and by employing the Wirtinger-type integral inequality, the convex approach, Green’s identity, the reciprocally convex approach, and Wirtinger’s inequality, an asymptotic stability criterion of the error system was established in terms of linear matrix inequalities (LMIs). The stability criterion depends upon the bounds of delays and their derivatives. It should be noted that if the set of LMIs is feasible, then the desired observation of DGRNs is possible, and the state estimation can be determined. Finally, two numerical examples are presented to illustrate the availability and applicability of the proposed scheme design. [ABSTRACT FROM AUTHOR]

An increasing number of neural memory networks have been developed, leading to the need for a systematic approach to analyze and compare their underlying memory structures. Thus, in this paper, we first create a framework for memory organization and then compare four popular dynamic models: vanilla recurrent neural network, long short-term memory, neural stack, and neural RAM. This analysis helps to open the dynamic neural networks’ black box from the memory usage prospective. Accordingly, a taxonomy for these networks and their variants is proposed and proved using a unifying architecture. With the taxonomy, both network architectures and learning tasks are classified into four classes, and a one-to-one mapping is built between them to help practitioners select the appropriate architecture. To exemplify each task type, four synthetic tasks with different memory requirements are selected. Moreover, we use some signal processing applications and two natural language processing applications to evaluate the methodology in a realistic setting. [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 introduces a convolutional neural network (CNN) approach to derive Volterra models of dynamical systems based on generalized orthonormal basis function (GOBF)-Volterra. The approach derives the parameters of the model through a CNN and the neural network’s learned weights represent the poles of a system. Simulation results show that the parameters of the system can be exactly recovered when no noise is applied. Furthermore, when noise is present, the errors in the parameters are very small for both the linear and nonlinear cases. Finally, the approach is used to identify the model of a quadcopter using data from actual flight tests. Comparisons with previous works demonstrate that CNNs can be satisfactorily used for the identification of dynamical systems. [ABSTRACT FROM AUTHOR]

This paper proposes a theory for understanding perceptual learning processes within the general framework of laws of nature. Artificial neural networks are regarded as systems whose connections are Lagrangian variables, namely, functions depending on time. They are used to minimize the cognitive action, an appropriate functional index that measures the agent interactions with the environment. The cognitive action contains a potential and a kinetic term that nicely resemble the classic formulation of regularization in machine learning. A special choice of the functional index, which leads to the fourth-order differential equations—Cognitive Action Laws (CAL)—exhibits a structure that mirrors classic formulation of machine learning. In particular, unlike the action of mechanics, the stationarity condition corresponds with the global minimum. Moreover, it is proven that typical asymptotic learning conditions on the weights can coexist with the initialization provided that the system dynamics is driven under a policy referred to as information overloading control. Finally, the theory is experimented for the problem of feature extraction in computer vision. [ABSTRACT FROM AUTHOR]

In this paper, a metacognitive octonion-valued neural network (Mc-OVNN) learning algorithm and its application to diverse time series prediction are presented. The Mc-OVNN is comprised of two components: the octonion-valued neural network that represents the cognitive component and the metacognitive component that serves to self-regulate the learning algorithm. At each epoch, the metacognitive component decides if, how, and when learning occurs. The algorithm deletes unneeded samples and only stores those that will be used. This decision is determined by the octonion magnitude and the seven phases. To evaluate the Mc-OVNN algorithm’s performance, it is applied to five real-world forecasting problems: the power consumption of a home in Honolulu, HI, USA, Box and Jenkins J series, Euro to Algerian Dinar (DZ) real-time conversion rates, the Mackey–Glass equation, and Europe Brent oil price prediction in a time series. When comparing the Mc-OVNN to other relevant techniques, Mc-OVNN displays its capability for efficient time series prediction. The real-time evaluation of the proposed algorithm is presented using the power consumption of a home in Boumerdès, Algeria, as a case study. [ABSTRACT FROM AUTHOR]

Dynamic behaviors of distribution networks are of great importance for the power system analysis. Nowadays, due to the integration of the renewable energy generation, energy storage, plug-in electric vehicles, and distribution networks turn from passive systems to active ones. Hence, the dynamic behaviors of active distribution networks (ADNs) are much more complex than the traditional ones. The research interests how to establish an accurate model of ADNs in modern power systems are drawing a great deal of attention. In this paper, motivated by the similarities between power system differential algebraic equations and the forward calculation flows of recurrent neural networks (RNNs), a long short-term memory (LSTM) RNN-based equivalent model is proposed to accurately represent the ADNs. First, the adoption reasons of the proposed LSTM RNN-based equivalent model are explained, and its advantages are analyzed from the mathematical point of view. Then, the accuracy and generalization performance of the proposed model is evaluated using the IEEE 39-Bus New England system integrated with ADNs in the study cases. It reveals that the proposed LSTM RNN-based equivalent model has a generalization capability to capture the dynamic behaviors of ADNs with high accuracy. [ABSTRACT FROM AUTHOR]

This paper presents a Hamiltonian-driven framework of adaptive dynamic programming (ADP) for continuous time nonlinear systems, which consists of evaluation of an admissible control, comparison between two different admissible policies with respect to the corresponding the performance function, and the performance improvement of an admissible control. It is showed that the Hamiltonian can serve as the temporal difference for continuous-time systems. In the Hamiltonian-driven ADP, the critic network is trained to output the value gradient. Then, the inner product between the critic and the system dynamics produces the value derivative. Under some conditions, the minimization of the Hamiltonian functional is equivalent to the value function approximation. An iterative algorithm starting from an arbitrary admissible control is presented for the optimal control approximation with its convergence proof. The implementation is accomplished by a neural network approximation. Two simulation studies demonstrate the effectiveness of Hamiltonian-driven ADP. [ABSTRACT FROM AUTHOR]

This paper presents a two-time-scale neurodynamic approach to constrained minimax optimization using two coupled neural networks. One of the recurrent neural networks is used for minimizing the objective function and another is used for maximization. It is shown that the coupled neurodynamic systems operating in two different time scales work well for minimax optimization. The effectiveness and characteristics of the proposed approach are illustrated using several examples. Furthermore, the proposed approach is applied for $H_\infty $ model predictive control. [ABSTRACT FROM PUBLISHER]

In this paper, an offline approximate dynamic programming approach using neural networks is proposed for solving a class of finite horizon stochastic optimal control problems. There are two approaches available in the literature, one based on stochastic maximum principle (SMP) formalism and the other based on solving the stochastic Hamilton–Jacobi–Bellman (HJB) equation. However, in the presence of noise, the SMP formalism becomes complex and results in having to solve a couple of backward stochastic differential equations. Hence, current solution methodologies typically ignore the noise effect. On the other hand, the inclusion of noise in the HJB framework is very straightforward. Furthermore, the stochastic HJB equation of a control-affine nonlinear stochastic system with a quadratic control cost function and an arbitrary state cost function can be formulated as a path integral (PI) problem. However, due to curse of dimensionality, it might not be possible to utilize the PI formulation for obtaining comprehensive solutions over the entire operating domain. A neural network structure called the adaptive critic design paradigm is used to effectively handle this difficulty. In this paper, a novel adaptive critic approach using the PI formulation is proposed for solving stochastic optimal control problems. The potential of the algorithm is demonstrated through simulation results from a couple of benchmark problems. [ABSTRACT FROM PUBLISHER]

Regarding two-player zero-sum games of continuous-time nonlinear systems with completely unknown dynamics, this paper presents an online adaptive algorithm for learning the Nash equilibrium solution, i.e., the optimal policy pair. First, for known systems, the simultaneous policy updating algorithm (SPUA) is reviewed. A new analytical method to prove the convergence is presented. Then, based on the SPUA, without using a priori knowledge of any system dynamics, an online algorithm is proposed to simultaneously learn in real time either the minimal nonnegative solution of the Hamilton–Jacobi–Isaacs (HJI) equation or the generalized algebraic Riccati equation for linear systems as a special case, along with the optimal policy pair. The approximate solution to the HJI equation and the admissible policy pair is reexpressed by the approximation theorem. The unknown constants or weights of each are identified simultaneously by resorting to the recursive least square method. The convergence of the online algorithm to the optimal solutions is provided. A practical online algorithm is also developed. Simulation results illustrate the effectiveness of the proposed method. [ABSTRACT FROM PUBLISHER]

This paper considers the basic Lazzaro winner-take-all analog computing circuit with $N$ current inputs, N$ voltage outputs, and a bias current. Motivated by low-power applications, we find a mathematical accurate model of the network when all MOS devices remain inside the subthreshold region all along the transient. This involves analytical inequalities relating the range of admissible input currents to transistor parameters, to supply voltage, and to bias current. The restrictions are sufficiently weak to allow extra demands of functionality or performance. The technical novelty here is that by a slight cut of the maximal subthreshold domain and by choosing proper coordinates, we get a ordinary differential equation invariance problem on a rectangle of \Re ^{N+1} space which is analytically tractable. A more precise localization of the asymptotically stable steady state inside the region of interest is also inferred. Although the work is mainly theoretical, an effort to infer simple, interpretable formulas useful for synthesis has been made. The results are numerically verified and their feasibility is discussed in detail. The subject matter is new and it is worth extending it to larger classes of circuits with regional behavior. [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]

Many practical problems can be solved by being formulated as time-varying quadratic programing (TVQP) problems. In this paper, a novel power-type varying-parameter recurrent neural network (VPNN) is proposed and analyzed to effectively solve the resulting TVQP problems, as well as the original practical problems. For a clear understanding, we introduce this model from three aspects: design, analysis, and applications. Specifically, the reason why and the method we use to design this neural network model for solving online TVQP problems subject to time-varying linear equality/inequality are described in detail. The theoretical analysis confirms that when activated by six commonly used activation functions, VPNN achieves a superexponential convergence rate. In contrast to the traditional zeroing neural network with fixed design parameters, the proposed VPNN has better convergence performance. Comparative simulations with state-of-the-art methods confirm the advantages of VPNN. Furthermore, the application of VPNN to a robot motion planning problem verifies the feasibility, applicability, and efficiency of the proposed method. [ABSTRACT FROM AUTHOR]

This paper studies the plume-tracing strategy for an autonomous underwater vehicle (AUV) in the deep-sea turbulent environment. The tracing problem is modeled as a partially observable Markov decision process with continuous state space and action space due to the spatio-temporal changes of environment. An long short-term memory-based reinforcement learning framework with full use of history information is proposed to generate a smooth strategy while the AUV interacting with the environment. Continuous temporal difference and deterministic policy gradient methods are employed to improve the strategy. To promote the performance of the algorithm, a supervised strategy generated by dynamic programming methods is utilized as transcendental knowledge of the agent. Historical searching trajectory’s form and the exploration technology are specially designed to fit the algorithm. Simulation environments are established based on Reynolds-averaged Navier–Stokes equations and the effectiveness of the learned plume-tracing strategy is validated with simulation experiments. [ABSTRACT FROM AUTHOR]

We study the problem of identifying the structure of a probabilistic Boolean network (PBN), a probabilistic model of biological networks, from a given set of samples. This problem can be regarded as an identification of a set of Boolean functions from samples. Existing studies on the identification of the structure of a PBN only use information on the occurrences of samples. In this paper, we also make use of the frequencies of occurrences of subtuples, information that is obtainable from the samples. We show that under this model, it is possible to identify a PBN from among a class of PBNs, for much broader classes of PBNs. In particular, we prove that, under a reasonable assumption, the structure of a PBN can be identified from among the class of PBNs that have at most three functions assigned to each node, but that identification may be impossible if four or more functions are assigned to each node. We also analyze the sample complexity for exactly identifying the structure of a PBN, and present an efficient algorithm for the identification of a PBN consisting of threshold functions from samples. [ABSTRACT FROM AUTHOR]

This paper is concerned with the multistability of switched neural networks with piecewise linear activation functions under state-dependent switching. Under some reasonable assumptions on the switching threshold and activation functions, by using the state-space decomposition method, contraction mapping theorem, and strictly diagonally dominant matrix theory, we can characterize the number of equilibria as well as analyze the stability/instability of the equilibria. More interesting, we can find that the switching threshold plays an important role for stable equilibria in the unsaturation regions of activation functions, and the number of stable equilibria of an $n$ -neuron switched neural network with state-dependent parameters increases to $3^{n}$ from $2^{n}$ in the conventional one. Furthermore, for two-neuron switched neural networks, the precise attraction basin of each stable equilibrium point can be figured out, and its boundary is composed of the stable manifolds of unstable equilibrium points and the switching lines. Two simulation examples are discussed in detail to substantiate the effectiveness of the theoretical analysis. [ABSTRACT FROM AUTHOR]

Benefited from quaternion representation that is able to encode the cross-channel correlation of color images, quaternion principle component analysis (QPCA) was proposed to extract features from color images while reducing the feature dimension. A quaternion covariance matrix (QCM) of input samples was constructed, and its eigenvectors were derived to find the solution of QPCA. However, eigen-decomposition leads to the fixed solution for the same input. This solution is susceptible to outliers and cannot be further optimized. To solve this problem, this paper proposes a novel quaternion ridge regression (QRR) model for two-dimensional QPCA (2D-QPCA). We mathematically prove that this QRR model is equivalent to the QCM model of 2D-QPCA. The QRR model is a general framework and is flexible to combine 2D-QPCA with other technologies or constraints to adapt different requirements of real-world applications. Including sparsity constraints, we then propose a quaternion sparse regression model for 2D-QSPCA to improve its robustness for classification. An alternating minimization algorithm is developed to iteratively learn the solution of 2D-QSPCA in the equivalent complex domain. In addition, 2D-QPCA and 2D-QSPCA can preserve the spatial structure of color images and have a low computation cost. Experiments on several challenging databases demonstrate that 2D-QPCA and 2D-QSPCA are effective in color face recognition, and 2D-QSPCA outperforms the state of the arts. [ABSTRACT FROM AUTHOR]

Universal memcomputing machines (UMMs) represent a novel computational model in which memory (time nonlocality) accomplishes both tasks of storing and processing of information. UMMs have been shown to be Turing-complete, namely, they can simulate any Turing machine. In this paper, we first introduce a novel set theory approach to compare different computational models and use it to recover the previous results on Turing-completeness of UMMs. We then relate UMMs directly to liquid-state machines (or “reservoir-computing”) and quantum machines (“quantum computing”). We show that UMMs can simulate both types of machines, hence they are both “liquid-” or “reservoir-complete” and “quantum-complete.” Of course, these statements pertain only to the type of problems these machines can solve and not to the amount of resources required for such simulations. Nonetheless, the set-theoretic method presented here provides a general framework which describes the relationship between any computational models. [ABSTRACT FROM AUTHOR]

Financial time-series forecasting has long been a challenging problem because of the inherently noisy and stochastic nature of the market. In the high-frequency trading, forecasting for trading purposes is even a more challenging task, since an automated inference system is required to be both accurate and fast. In this paper, we propose a neural network layer architecture that incorporates the idea of bilinear projection as well as an attention mechanism that enables the layer to detect and focus on crucial temporal information. The resulting network is highly interpretable, given its ability to highlight the importance and contribution of each temporal instance, thus allowing further analysis on the time instances of interest. Our experiments in a large-scale limit order book data set show that a two-hidden-layer network utilizing our proposed layer outperforms by a large margin all existing state-of-the-art results coming from much deeper architectures while requiring far fewer computations. [ABSTRACT FROM AUTHOR]

Partial least squares regression (PLSR) has been a popular technique to explore the linear relationship between two data sets. However, all existing approaches often optimize a PLSR model in Euclidean space and take a successive strategy to calculate all the factors one by one for keeping the mutually orthogonal PLSR factors. Thus, a suboptimal solution is often generated. To overcome the shortcoming, this paper takes statistically inspired modification of PLSR (SIMPLSR) as a representative of PLSR, proposes a novel approach to transform SIMPLSR into optimization problems on Riemannian manifolds, and develops corresponding optimization algorithms. These algorithms can calculate all the PLSR factors simultaneously to avoid any suboptimal solutions. Moreover, we propose sparse SIMPLSR on Riemannian manifolds, which is simple and intuitive. A number of experiments on classification problems have demonstrated that the proposed models and algorithms can get lower classification error rates compared with other linear regression methods in Euclidean space. We have made the experimental code public at https://github.com/Haoran2014. [ABSTRACT FROM AUTHOR]