Search

This paper provides a review of design approaches towards artificial intelligence (AI) System-on-Chip. AI algorithms have progressed over the past decades from perceptron-based neural network (NN) and neuro-fuzzy (NF) system to today’s deep neural network (DNN) and neuromorphic computing. Recent DNN hardware accelerators focus on energy-efficient integration of digital circuits to realize real-time DNN operation while neuromorphic processors deploy new memory technologies with analog computation for low power consumption. However, different design approaches can be applied to such processor implementation with their pros and cons. This paper reviews from the early processor designs for NN and NF in both mixed-mode and digital implementations to the recent DNN SoC designs that we have proposed for a decade. The former content deals with NN and NF processors used as a functional building block of a machine vision SoC, while the latter concentrates on integration of the whole DNN function. We also provide a discussion on the approaches, and provide perspective on future research directions. [ABSTRACT FROM AUTHOR]

Computing-in-memory (CIM) is a promising approach to reduce the latency and improve the energy efficiency of deep neural network (DNN) artificial intelligence (AI) edge processors. However, SRAM-based CIM (SRAM-CIM) faces practical challenges in terms of area overhead, performance, energy efficiency, and yield against variations in data patterns and transistor performance. This paper employed a circuit-system co-design methodology to develop a SRAM-CIM unit-macro for a binary-based fully connected neural network (FCNN) layer of the DNN AI edge processors. The proposed SRAM-CIM unit-macro supports two binarized neural network models: an XNOR neural network (XNORNN) and a modified binary neural network (MBNN). To achieve compact area, fast access time, robust operations, and high energy-efficiency, our proposed SRAM-CIM uses a split-wordline compact-rule 6T SRAM and circuit techniques, including a dynamic input-aware reference generation (DIARG) scheme, an algorithm-dependent asymmetric control (ADAC) scheme, a write disturb-free (WDF) scheme, and a common-mode-insensitive small offset voltage-mode sensing amplifier (CMI-VSA). A fabricated 65-nm 4-Kb SRAM-CIM unit-macro achieved 2.4- and 2.3-ns product-sum access times for a FCNN layer using XNORNN and MBNN, respectively. The measured maximum energy efficiency reached 30.49 TOPS/W for XNORNN and 55.8 TOPS/W for the MBNN modes. [ABSTRACT FROM AUTHOR]

Conservation principles, such as conservation of charge, energy, or mass, provide a natural way to couple and constrain spatially separated variables. In this paper, we propose a dynamical system model that exploits these constraints for solving nonconvex and discrete global optimization problems. Unlike the traditional simulated annealing or quantum annealing-based global optimization techniques, the proposed method optimizes a target objective function by continuously evolving a driver functional over a conservation manifold, using a generalized variant of growth transformations. As a result, the driver functional asymptotically converges toward a Dirac-delta function that is centered at the global optimum of the target objective function. In this paper, we provide an outline of the proof of convergence for the dynamical system model and investigate different properties of the model using a benchmark nonlinear optimization problem. Also, we demonstrate how a discrete variant of the proposed dynamical system can be used for implementing decentralized optimization algorithms, where an ensemble of spatially separated entities (for example, biological cells or simple computational units) can collectively implement specific functions, such as winner-take-all and ranking, by exchanging signals only with its immediate substrate or environment. The proposed dynamical system model could potentially be used to implement continuous-time optimizers, annealers, and neural networks. [ABSTRACT FROM AUTHOR]

Hyperdimensional (HD) computing is a promising paradigm for future intelligent electronic appliances operating at low power. This paper discusses tradeoffs of selecting parameters of binary HD representations when applied to pattern recognition tasks. Particular design choices include density of representations and strategies for mapping data from the original representation. It is demonstrated that for the considered pattern recognition tasks (using synthetic and real-world data) both sparse and dense representations behave nearly identically. This paper also discusses implementation peculiarities which may favor one type of representations over the other. Finally, the capacity of representations of various densities is discussed. [ABSTRACT FROM AUTHOR]

With explosive growth of data volume and ever-increasing diversity of data modalities, cross-modal similarity search, which conducts nearest neighbor search across different modalities, has been attracting increasing interest. This paper presents a deep compact code learning solution for efficient cross-modal similarity search. Many recent studies have proven that quantization-based approaches perform generally better than hashing-based approaches on single-modal similarity search. In this paper, we propose a deep quantization approach, which is among the early attempts of leveraging deep neural networks into quantization-based cross-modal similarity search. Our approach, dubbed shared predictive deep quantization (SPDQ), explicitly formulates a shared subspace across different modalities and two private subspaces for individual modalities, and representations in the shared subspace and the private subspaces are learned simultaneously by embedding them to a reproducing kernel Hilbert space, where the mean embedding of different modality distributions can be explicitly compared. In addition, in the shared subspace, a quantizer is learned to produce the semantics preserving compact codes with the help of label alignment. Thanks to this novel network architecture in cooperation with supervised quantization training, SPDQ can preserve intramodal and intermodal similarities as much as possible and greatly reduce quantization error. Experiments on two popular benchmarks corroborate that our approach outperforms state-of-the-art methods. [ABSTRACT FROM AUTHOR]

In the first issue of Nature 2015, Google DeepMind published a paper “Human-level control through deep reinforcement learning.” Furthermore, in the first issue of Nature 2016, it published a cover paper “Mastering the game of Go with deep neural networks and tree search” and proposed the computer Go program, AlphaGo. In March 2016, AlphaGo beat the world’s top Go player Lee Sedol by 4:1. This becomes a new milestone in artificial intelligence history, the core of which is the algorithm of deep reinforcement learning (RL). [ABSTRACT FROM AUTHOR]

This paper presents the Chebyshev neural network (ChNN) as an improved artificial intelligence technique for power system protection studies and examines the performances of two ChNN learning algorithms for fault classification of series compensated transmission line. The training algorithms are least-square Levenberg–Marquardt (LSLM) and recursive least-square algorithm with forgetting factor (RLSFF). The performances of these algorithms are assessed based on their generalization capability in relating the fault current parameters with an event of fault in the transmission line. The proposed algorithm is fast in response as it utilizes postfault samples of three phase currents measured at the relaying end corresponding to half-cycle duration only. After being trained with only a small part of the generated fault data, the algorithms have been tested over a large number of fault cases with wide variation of system and fault parameters. Based on the studies carried out in this paper, it has been found that although the RLSFF algorithm is faster for training the ChNN in the fault classification application for series compensated transmission lines, the LSLM algorithm has the best accuracy in testing. The results prove that the proposed ChNN-based method is accurate, fast, easy to design, and immune to the level of compensations. Thus, it is suitable for digital relaying applications. [ABSTRACT FROM PUBLISHER]

Batch normalization (BN) has recently become a standard component for accelerating and improving the training of deep neural networks (DNNs). However, BN brings in additional calculations, consumes more memory, and significantly slows down the training iteration. Furthermore, the nonlinear square and sqrt operations in the normalization process impede low bit-width quantization techniques, which draw much attention to the deep learning hardware community. In this paper, we propose an $L1$ -norm BN (L1BN) with only linear operations in both forward and backward propagations during training. L1BN is approximately equivalent to the conventional $L2$ -norm BN (L2BN) by multiplying a scaling factor that equals $({\pi }/{2})^{1/2}$. Experiments on various convolutional neural networks and generative adversarial networks reveal that L1BN can maintain the same performance and convergence rate as L2BN but with higher computational efficiency. In real application-specified integrated circuit synthesis with reduced resources, L1BN achieves 25% speedup and 37% energy saving compared to the original L2BN. Our hardware-friendly normalization method not only surpasses L2BN in speed but also simplifies the design of deep learning accelerators. Last but not least, L1BN promises a fully quantized training of DNNs, which empowers future artificial intelligence applications on mobile devices with transfer and continual learning capability. [ABSTRACT FROM AUTHOR]

Since neural networks renaissance, convolutional neural networks (ConvNets) have demonstrated a state-of-the-art performance in several emerging artificial intelligence tasks. The deployment of ConvNets in real-life applications requires power-efficient designs that meet the application-level performance needs. In this context, field-programmable gate arrays (FPGAs) can provide a potential platform that can be tailored to application-specific requirements. However, with the complexity of ConvNet models increasing rapidly, the ConvNet-to-FPGA design space becomes prohibitively large. This paper presents fpgaConvNet, an end-to-end framework for the optimized mapping of ConvNets on FPGAs. The proposed framework comprises an automated design methodology based on the synchronous dataflow (SDF) paradigm and defines a set of SDF transformations in order to efficiently navigate the architectural design space. By proposing a systematic multiobjective optimization formulation, the presented framework is able to generate hardware designs that are cooptimized for the ConvNet workload, the target device, and the application’s performance metric of interest. Quantitative evaluation shows that the proposed methodology yields hardware designs that improve the performance by up to $6.65\times $ over highly optimized graphics processing unit designs for the same power constraints and achieve up to $2.94\times $ higher performance density compared with the state-of-the-art FPGA-based ConvNet architectures. [ABSTRACT FROM AUTHOR]

This paper investigates the exponential stability analysis issue for a class of delayed recurrent neural networks (RNNs) with semi-Markovian parameters. By constructing a stochastic Lyapunov functional and using some zoom techniques to estimate its weak infinitesimal operator, the exponential mean square stability criteria have been proposed for the Markovian neural networks with certain transition probabilities. We then generalize the homogeneous polynomial approach for the delayed Markovian RNNs with uncertain transition probabilities during the stability analysis. Theoretical results have obtained by introducing an appropriate technique for dealing with a large number of complex homogeneous polynomial matrix inequalities. Finally, numerical examples are provided to demonstrate the effectiveness of the proposed technique. [ABSTRACT FROM AUTHOR]

In this paper, kurtosis-based complex-valued real-time recurrent learning (KCRTRL) and kurtosis-based augmented CRTRL (KACRTRL) algorithms are proposed for training fully connected recurrent neural networks (FCRNNs) in the complex domain. These algorithms are designed by minimizing the cost functions based on the kurtosis of a complex-valued error signal. The KCRTRL algorithm exploits the circularity properties of the complex-valued signals, and this algorithm not only provides a faster convergence rate but also results in a lower steady-state error. However, the KCRTRL algorithm is suboptimal in the processing of noncircular (NC) complex-valued signals. On the other hand, the KACRTRL algorithm contains a complete second-order information due to the augmented statistics, thus considerably improves the performance of the FCRNN in the processing of NC complex-valued signals. Simulation results on the one-step-ahead prediction problems show that the proposed KCRTRL algorithm significantly enhances the performance for only circular complex-valued signals, whereas the proposed KACRTRL algorithm provides more superior performance than existing algorithms for NC complex-valued signals in terms of the convergence rate and the steady-state error. [ABSTRACT FROM AUTHOR]

Deep convolutional neural networks (CNNs) have become a key element in the recent breakthrough of salient object detection. However, existing CNN-based methods are based on either patchwise (regionwise) training and inference or fully convolutional networks. Methods in the former category are generally time-consuming due to severe storage and computational redundancies among overlapping patches. To overcome this deficiency, methods in the second category attempt to directly map a raw input image to a predicted dense saliency map in a single network forward pass. Though being very efficient, it is arduous for these methods to detect salient objects of different scales or salient regions with weak semantic information. In this paper, we develop hybrid contrast-oriented deep neural networks to overcome the aforementioned limitations. Each of our deep networks is composed of two complementary components, including a fully convolutional stream for dense prediction and a segment-level spatial pooling stream for sparse saliency inference. We further propose an attentional module that learns weight maps for fusing the two saliency predictions from these two streams. A tailored alternate scheme is designed to train these deep networks by fine-tuning pretrained baseline models. Finally, a customized fully connected conditional random field model incorporating a salient contour feature embedding can be optionally applied as a postprocessing step to improve spatial coherence and contour positioning in the fused result from these two streams. Extensive experiments on six benchmark data sets demonstrate that our proposed model can significantly outperform the state of the art in terms of all popular evaluation metrics. [ABSTRACT FROM AUTHOR]

Nowadays, the control technology of the robotic manipulator with flexible joints (RMFJ) is not mature enough. The flexible-joint manipulator dynamic system possesses many uncertainties, which brings a great challenge to the controller design. This paper is motivated by this problem. In order to deal with this and enhance the system robustness, the full-state feedback neural network (NN) control is proposed. Moreover, output constraints of the RMFJ are achieved, which improve the security of the robot. Through the Lyapunov stability analysis, we identify that the proposed controller can guarantee not only the stability of flexible-joint manipulator system but also the boundedness of system state variables by choosing appropriate control gains. Then, we make some necessary simulation experiments to verify the rationality of our controllers. Finally, a series of control experiments are conducted on the Baxter. By comparing with the proportional–derivative control and the NN control with the rigid manipulator model, the feasibility and the effectiveness of NN control based on flexible-joint manipulator model are verified. [ABSTRACT FROM AUTHOR]

In this paper, we present an approach for minimizing the computational complexity of the trained convolutional neural networks (ConvNets). The idea is to approximate all elements of a given ConvNet and replace the original convolutional filters and parameters (pooling and bias coefficients; and activation function) with an efficient approximations capable of extreme reductions in computational complexity. Low-complexity convolution filters are obtained through a binary (zero and one) linear programming scheme based on the Frobenius norm over sets of dyadic rationals. The resulting matrices allow for multiplication-free computations requiring only addition and bit-shifting operations. Such low-complexity structures pave the way for low power, efficient hardware designs. We applied our approach on three use cases of different complexities: 1) a “light” but efficient ConvNet for face detection (with around 1000 parameters); 2) another one for hand-written digit classification (with more than 180 000 parameters); and 3) a significantly larger ConvNet: AlexNet with $\approx 1.2$ million matrices. We evaluated the overall performance on the respective tasks for different levels of approximations. In all considered applications, very low-complexity approximations have been derived maintaining an almost equal classification performance. [ABSTRACT FROM AUTHOR]

This paper focuses on the event-triggered guaranteed cost control design of nonlinear systems via a self-learning technique. In brief, an event-based guaranteed cost control strategy of nonlinear systems subjects to matched uncertainties is developed, thereby balancing the performance of guaranteed cost and the actuality of limited communication resource. The original control design is transformed into an optimal control problem with an event-based mechanism, where the relationship of guaranteed cost performance compared to the time-based formulation is discussed. A critic neural network is constructed for implementing the event-based optimal control design with stability guarantee. Simulation experiments are carried out to verify the theoretical results in detail. [ABSTRACT FROM AUTHOR]

Most existing object detection algorithms are trained based upon a set of fully annotated object regions or bounding boxes, which are typically labor-intensive. On the contrary, nowadays there is a significant amount of image-level annotations cheaply available on the Internet. It is hence a natural thought to explore such “weak” supervision to benefit the training of object detectors. In this paper, we propose a novel scheme to perform weakly supervised object localization, termed object-specific pixel gradient (OPG). The OPG is trained by using image-level annotations alone, which performs in an iterative manner to localize potential objects in a given image robustly and efficiently. In particular, we first extract an OPG map to reveal the contributions of individual pixels to a given object category, upon which an iterative mining scheme is further introduced to extract instances or components of this object. Moreover, a novel average and max pooling layer is introduced to improve the localization accuracy. In the task of weakly supervised object localization, the OPG achieves a state-of-the-art 44.5% top-5 error on ILSVRC 2013, which outperforms competing methods, including Oquabet al.and region-based convolutional neural networks on the Pascal VOC 2012, with gains of 2.6% and 2.3%, respectively. In the task of object detection, OPG achieves a comparable performance of 27.0% mean average precision on Pascal VOC 2007. In all experiments, the OPG only adopts the off-the-shelf pretrained CNN model, without using any object proposals. Therefore, it also significantly improves the detection speed, i.e., achieving three times faster compared with the state-of-the-art method. [ABSTRACT FROM AUTHOR]

The robust Huber’s M-estimator is widely used in signal and image processing, classification, and regression. From an optimization point of view, Huber’s M-estimation problem is often formulated as a large-sized quadratic programming (QP) problem in view of its nonsmooth cost function. This paper presents a generalized regression estimator which minimizes a reduced-sized QP problem. The generalized regression estimator may be viewed as a significant generalization of several robust regression estimators including Huber’s M-estimator. The performance of the generalized regression estimator is analyzed in terms of robustness and approximation accuracy. Furthermore, two low-dimensional recurrent neural networks (RNNs) are introduced for robust estimation. The two RNNs have low model complexity and enhanced computational efficiency. Finally, the experimental results of two examples and an application to image restoration are presented to substantiate superior performance of the proposed method over conventional algorithms for robust regression estimation in terms of approximation accuracy and convergence rate. [ABSTRACT FROM AUTHOR]

An intelligent data-driven predictive control strategy is proposed in this paper. The predictive controller is designed by combining predictive control and local weighted projection regression. The presented control strategy needs less prior knowledge and has fewer parameters that are hard to determine compared to other data-driven predictive controller, e.g., the one in dynamic partial least square (PLS) framework. Furthermore, the proposed predictive controller performs better in the control of nonlinear processes and is able to update its parameters based on the online data. The predictive model validity and intelligence of the control strategy are guaranteed by the online updating strategy to a certain degree. The control performance of the proposed predictive controller against the model predictive control (MPC) in dynamic PLS framework is illustrated through the simulation of a typical numerical example and the benchmark of a continuous stirred tank heater system. It can be observed from the simulation that the proposed MPC strategy has higher prediction precision and stronger ability in coping with nonlinear dynamic processes which are quite common in practical applications, for instance, the industrial process. [ABSTRACT FROM AUTHOR]

Image captioning aims to generate natural language sentences to describe the salient parts of a given image. Although neural networks have recently achieved promising results, a key problem is that they can only describe concepts seen in the training image-sentence pairs. Efficient learning of novel concepts has thus been a topic of recent interest to alleviate the expensive manpower of labeling data. In this paper, we propose a novel method,Image-Text Surgery, to synthesize pseudoimage-sentence pairs. The pseudopairs are generated under the guidance of a knowledge base, with syntax from a seed data set (i.e., MSCOCO) and visual information from an existing large-scale image base (i.e., ImageNet). Via pseudodata, the captioning model learns novel concepts without any corresponding human-labeled pairs. We further introduce adaptive visual replacement, which adaptively filters unnecessary visual features in pseudodata with an attention mechanism. We evaluate our approach on a held-out subset of the MSCOCO data set. The experimental results demonstrate that the proposed approach provides significant performance improvements over state-of-the-art methods in terms of F1 score and sentence quality. An ablation study and the qualitative results further validate the effectiveness of our approach. [ABSTRACT FROM AUTHOR]

In this paper, we propose a novel adaptive piecewise linear model for dynamic system identification. It has four unique features. First, the model designs a new kind of basis function for function approximation. It maintains the uniform shape for each basis function, so as to achieve a satisfactory tradeoff between generalization ability and model complexity. Second, the model takes the structure of basis functions as decision variables to optimize the formulated identification problems instead of taking expansion coefficients as decision variables as proposed by many existing approaches. Third, we establish an incremental design strategy to solve the system identification problems. In each step of the identification, the selection of optimal basis function is a Lipschitz continuous optimization problem that is likely to be easily handled with some mature toolboxes. This incremental design strategy greatly reduces the estimation cost. Fourth, we introduce a smoothing mechanism to avoid overfitting, when the output of dynamic systems is disturbed by noise. Tests on several benchmark dynamic systems demonstrate the potential of the proposed model. [ABSTRACT FROM AUTHOR]

Learning discriminative feature representations has shown remarkable importance due to its promising performance for machine learning problems. This paper presents a discriminative data representation learning framework by employing a simple yet powerful marginal regression function with probabilistic graphical structure adaptation. A marginally structured representation learning (MSRL) method is proposed by seamlessly incorporating distinguishable regression targets analysis, graph structure adaptation, and robust linear structural learning into a joint framework. Specifically, MSRL learns marginal regression targets from data rather than exploiting the conventional zero–one matrix that greatly hinders the freedom of regression fitness and degrades the performance of regression results. Meanwhile, an optimized graph regularization term with self-improving adaptation is constructed based on probabilistic connection knowledge to improve the compactness of the learned representation. Additionally, the regression targets are further predicted by utilizing the explanatory factors from the latent subspace of data, which can uncover the underlying feature correlations to enhance the reliability. The resulting optimization problem can be elegantly solved by an efficient iterative algorithm. Finally, the proposed method is evaluated by eight diverse but related tasks, including object, face, texture, and scene, categorization data sets. The encouraging experimental results and the explicit theoretical analysis demonstrate the efficacy of the proposed representation learning method in comparison with state-of-the-art algorithms. [ABSTRACT FROM AUTHOR]

In this paper, the stability problem is studied for a class of stochastic neural networks (NNs) with local impulsive effects. The impulsive effects considered can be not only nonidentical in different dimensions of the system state but also various at distinct impulsive instants. Hence, the impulses here can encompass several typical impulses in NNs. The aim of this paper is to derive stability criteria such that stochastic NNs with local impulsive effects are exponentially stable in mean square. By means of the mathematical induction method, several easy-to-check conditions are obtained to ensure the mean square stability of NNs. Three examples are given to show the effectiveness of the proposed stability criterion. [ABSTRACT FROM PUBLISHER]

This paper focuses on the deep and shallow architecture of multilayer neural networks (MNNs). The demonstration of whether or not an MNN can be replaced by another MNN with fewer layers is equivalent to studying the topological conjugacy of its hidden layers. This paper provides a systematic methodology to indicate when two hidden spaces are topologically conjugated. Furthermore, some criteria are presented for some specific cases. [ABSTRACT FROM PUBLISHER]

This paper investigates how to train a recurrent neural network (RNN) using the Levenberg–Marquardt (LM) algorithm as well as how to implement optimal control of a grid-connected converter (GCC) using an RNN. To successfully and efficiently train an RNN using the LM algorithm, a new forward accumulation through time (FATT) algorithm is proposed to calculate the Jacobian matrix required by the LM algorithm. This paper explores how to incorporate FATT into the LM algorithm. The results show that the combination of the LM and FATT algorithms trains RNNs better than the conventional backpropagation through time algorithm. This paper presents an analytical study on the optimal control of GCCs, including theoretically ideal optimal and suboptimal controllers. To overcome the inapplicability of the optimal GCC controller under practical conditions, a new RNN controller with an improved input structure is proposed to approximate the ideal optimal controller. The performance of an ideal optimal controller and a well-trained RNN controller was compared in close to real-life power converter switching environments, demonstrating that the proposed RNN controller can achieve close to ideal optimal control performance even under low sampling rate conditions. The excellent performance of the proposed RNN controller under challenging and distorted system conditions further indicates the feasibility of using an RNN to approximate optimal control in practical applications. [ABSTRACT FROM AUTHOR]

This paper considers a class of nonsymmetric cooperative neural networks (NNs) where the neurons are fully interconnected and the neuron activations are modeled by piecewise linear (PL) functions. The solution semiflow generated by cooperative PLNNs is monotone but, due to the horizontal segments in the neuron activations, is not eventually strongly monotone (ESM). The main result in this paper is that it is possible to prove a peculiar form of the Limit Set Dichotomy for this class of cooperative PLNNs. Such a form is slightly weaker than the standard form valid for ESM semiflows, but this notwithstanding it permits to establish a result on convergence analogous to that valid for ESM semiflows. Namely, for almost every choice of the initial conditions, each solution of a fully interconnected cooperative PLNN converges toward an equilibrium point, depending on the initial conditions, as t \to +\infty. From a methodological viewpoint, this paper extends some basic techniques and tools valid for ESM semiflows, in order that they can be applied to the monotone semiflows generated by the considered class of cooperative PLNNs. [ABSTRACT FROM PUBLISHER]

This paper develops a neural network for solving the general nonsmooth convex optimization problems. The proposed neural network is modeled by a differential inclusion. Compared with the existing neural networks for solving nonsmooth convex optimization problems, this neural network has a wider domain for implementation. Under a suitable assumption on the constraint set, it is proved that for a given nonsmooth convex optimization problem and sufficiently large penalty parameters, any trajectory of the neural network can reach the feasible region in finite time and stays there thereafter. Moreover, we can prove that the trajectory of the neural network constructed by a differential inclusion and with arbitrarily given initial value, converges to the set consisting of the equilibrium points of the neural network, whose elements are all the optimal solutions of the primal constrained optimization problem. In particular, we give the condition that the equilibrium point set of the neural network coincides with the optimal solution set of the primal constrained optimization problem and the condition ensuring convergence to the optimal solution set in finite time. Furthermore, illustrative examples show the correctness of the results in this paper, and the good performance of the proposed neural network. [ABSTRACT FROM AUTHOR]

The paper addresses analytical and practical aspects of integration of equation-based (classical) and signal-derived [artificial neural network (ANN)] dynamic models for transient analysis of large-scale dynamical systems. Our signal-based part is based on two ANNs, and is derived from measurements at boundary points. In this paper, we describe this hybrid modeling technique, and focus on: 1) a least square-based mechanism for on-line correction of dynamic variable predictions that is based on actual operating conditions; 2) the resilience of the algorithm to missing measurements due to failed communication links; and 3) a complete two-way interaction between the differential-algebraic equation based subsystem and the ANN-based subsystem. The paper demonstrates the feasibility of implementing our approach in standard power system software by integrating the ANN-based model with the transient analysis toolbox from Matlab. We illustrate capabilities of the proposed approach for transient analysis on a benchmark multi-machine example derived from the New England/New-York interconnected power system. [ABSTRACT FROM AUTHOR]

Recurrent neural networks of the Lotka-Volterra model have been proven to possess characteristics which are desirable in some neural computations. A clear understanding of the dynamical properties of a recurrent neural network is necessary for efficient applications of the network. This paper studies the global convergence of general Lotka-Volterra recurrent neural networks with variable delays. The contributions of this paper are: 1) sufficient conditions are established for lower positive boundedness of the networks; 2) global exponential stability conditions are obtained for the networks. These conditions are totally independent of the variable delays which are therefore allowed to be uncertain; 3) novel Lyapunov functionals are constructed to establish delays dependent conditions for global asymptotic stability, and 4) simulation results and examples are provided to supplement and illustrate the theoretical contributions presented. [ABSTRACT FROM AUTHOR]

Multistable networks have attracted much interest in recent years, since multistability is of primary importance for some applications of recurrent neural networks where monostability exhibits some restrictions. This paper focuses on the analysis of dynamical property for a class of additive recurrent neural networks with nonsaturating linear threshold transfer functions. A milder condition is derived to guarantee the boundedness and global attractivity of the networks as compared to that presented in [6]. Dynamical properties of the equilibria of two-dimensional networks are analyzed theoretically, and the relationships between the equilibria features and network parameters (synaptic weights and external inputs) are revealed. In addition, the sufficient and necessary conditions for coexistence of multiple equilibria are obtained, which confirmed the observations in [14] with a cortex-inspired silicon circuit. The results obtained in this paper are applicable to both symmetric and nonsymmetric networks. Simulation examples are used to illustrate the theory developed in this paper. [ABSTRACT FROM AUTHOR]

This paper deals with the global convergence and stability of the Hopfield-type neural networks under the critical condition that M1(F) = L-1DF - (FW+WTF)/(2) is nonnegative for any diagonal matrix F, where W is the weight matrix of the network, L = diag(L1, L2,.. . , LN) with 4 being the Lipschitz constant of gi and G(u) = (g1(u1),g2(u2),. . ,gN(uN))T is the activation mapping of the network. Many stability results have been obtained for the Hopfield-type neural networks in the noncritical case that M1 (F) is positive definite for some positive definite diagonal matrix F. However, very few results are available on the global convergence and stability of the networks in the critical case. In this paper, by exploring two intrinsic features of the activation mapping, two generic global convergence results are established in the critical case for the Hopfield-type neural networks, which extend most of the previously known globally asymptotic stability criteria to the critical case. The results obtained discriminate the critical dynamics of the networks, and can be applied directly to a group of Hopfield-type neural network models. An example has also been presented to demonstrate both theoretical importance and practical significance of the critical results obtained. [ABSTRACT FROM AUTHOR]

In this paper, a novel paradigm for blind source separation in the presence of nonlinear mixtures is presented. In particular, the paper addresses the problem of post-nonlinear mixing followed by another instantaneous mixing system. This model is called here the post-nonlinear-linear model. The method is based on the use of the recently introduced flexible activation function whose control points are adaptively changed: a neural model based on adaptive B-spline functions is employed. The signal separation is achieved through an information maximization criterion. Experimental results and comparison with existing solutions confirm the effectiveness of the proposed architecture. [ABSTRACT FROM AUTHOR]

Sequence transfer learning is of interest in both academia and industry with the emergence of numerous new text domains from Twitter and other social media tools. In this paper, we put forward the data-sensitive granularity for transfer learning, and then, a novel substructural regularization transfer learning model (STLM) is proposed to preserve target domain features at substructural granularity in the light of the condition of labeled data set size. Our model is underpinned by hidden Markov model and regularization theory, where the substructural representation can be integrated as a penalty after measuring the dissimilarity of substructures between target domain and STLM with relative entropy. STLM can achieve the competing goals of preserving the target domain substructure and utilizing the observations from both the target and source domains simultaneously. The estimation of STLM is very efficient since an analytical solution can be derived as a necessary and sufficient condition. The relative usability of substructures to act as regularization parameters and the time complexity of STLM are also analyzed and discussed. Comprehensive experiments of part-of-speech tagging with both Brown and Twitter corpora fully justify that our model can make improvements on all the combinations of source and target domains. [ABSTRACT FROM AUTHOR]

This paper focuses on the connecting structure of deep neural networks and proposes a layerwise structure learning method based on multiobjective optimization. A model with better generalization can be obtained by reducing the connecting parameters in deep networks. The aim is to find the optimal structure with high representation ability and better generalization for each layer. Then, the visible data are modeled with respect to structure based on the products of experts. In order to mitigate the difficulty of estimating the denominator in PoE, the denominator is simplified and taken as another objective, i.e., the connecting sparsity. Moreover, for the consideration of the contradictory nature between the representation ability and the network connecting sparsity, the multiobjective model is established. An improved multiobjective evolutionary algorithm is used to solve this model. Two tricks are designed to decrease the computational cost according to the properties of input data. The experiments on single-layer level, hierarchical level, and application level demonstrate the effectiveness of the proposed algorithm, and the learned structures can improve the performance of deep neural networks. [ABSTRACT FROM AUTHOR]

This paper is devoted to distributed adaptive containment control for a class of nonlinear multiagent systems with input quantization. By employing a matrix factorization and a novel matrix normalization technique, some assumptions involving control gain matrices in existing results are relaxed. By fusing the techniques of sliding mode control and backstepping control, a two-step design method is proposed to construct controllers and, with the aid of neural networks, all system nonlinearities are allowed to be unknown. Moreover, a linear time-varying model and a similarity transformation are introduced to circumvent the obstacle brought by quantization, and the controllers need no information about the quantizer parameters. The proposed scheme is able to ensure the boundedness of all closed-loop signals and steer the containment errors into an arbitrarily small residual set. The simulation results illustrate the effectiveness of the scheme. [ABSTRACT FROM AUTHOR]

As data sets become larger and more complicated, an extreme learning machine (ELM) that runs in a traditional serial environment cannot realize its ability to be fast and effective. Although a parallel ELM (PELM) based on MapReduce to process large-scale data shows more efficient learning speed than identical ELM algorithms in a serial environment, some operations, such as intermediate results stored on disks and multiple copies for each task, are indispensable, and these operations create a large amount of extra overhead and degrade the learning speed and efficiency of the PELMs. In this paper, an efficient ELM based on the Spark framework (SELM), which includes three parallel subalgorithms, is proposed for big data classification. By partitioning the corresponding data sets reasonably, the hidden layer output matrix calculation algorithm, matrix \mathbf \hat U decomposition algorithm, and matrix \mathbf V decomposition algorithm perform most of the computations locally. At the same time, they retain the intermediate results in distributed memory and cache the diagonal matrix as broadcast variables instead of several copies for each task to reduce a large amount of the costs, and these actions strengthen the learning ability of the SELM. Finally, we implement our SELM algorithm to classify large data sets. Extensive experiments have been conducted to validate the effectiveness of the proposed algorithms. As shown, our SELM achieves an $8.71\times$ speedup on a cluster with ten nodes, and reaches a $13.79\times$ speedup with 15 nodes, an $18.74\times$ speedup with 20 nodes, a $23.79\times$ speedup with 25 nodes, a $28.89\times$ speedup with 30 nodes, and a $33.81\times$ speedup with 35 nodes. [ABSTRACT FROM AUTHOR]

In numerous industrial applications where safety, efficiency, and reliability are among primary concerns, condition-based maintenance (CBM) is often the most effective and reliable maintenance policy. Prognostics, as one of the key enablers of CBM, involves the core task of estimating the remaining useful life (RUL) of the system. Neural networks-based approaches have produced promising results on RUL estimation, although their performances are influenced by handcrafted features and manually specified parameters. In this paper, we propose a multiobjective deep belief networks ensemble (MODBNE) method. MODBNE employs a multiobjective evolutionary algorithm integrated with the traditional DBN training technique to evolve multiple DBNs simultaneously subject to accuracy and diversity as two conflicting objectives. The eventually evolved DBNs are combined to establish an ensemble model used for RUL estimation, where combination weights are optimized via a single-objective differential evolution algorithm using a task-oriented objective function. We evaluate the proposed method on several prognostic benchmarking data sets and also compare it with some existing approaches. Experimental results demonstrate the superiority of our proposed method. [ABSTRACT FROM AUTHOR]

This paper is concerned with global asymptotic stability of a class of Cohen–Grossberg bidirectional associative memory (BAM) neural networks with delays. Under the assumptions that the activation functions only satisfy the so-called extended global Lipschitz condition and the behaved functions only satisfy global Lipschitz condition, we apply linear matrix inequality (LMI) method and homeomorphism theory to propose a new LMI-based sufficient condition for global asymptotic stability of the concerned neural networks. In our results, the extended global Lipschitz condition on the activation functions is less conservative than the assumptions for boundedness and monotonicity and is weaker than the assumption for the general global Lipschitz condition, the global Lipschitz condition on the behaved functions is also less conservative than the assumptions for monotonicity and differentiability in existing papers. [ABSTRACT FROM AUTHOR]

Text entry from people is not only grammatical and distinct, but also noisy. For example, a user's typing stream contains all the information about the user's interaction with computer using a QWERTY keyboard, which may include the user's typing mistakes as well as specific vocabulary, typing habit, and typing performance. In particular, these features are obvious in disabled users' typing streams. This paper proposes a new concept called noisy language modeling by further developing information theory and applies neural networks to one of its specific application-typing stream. This paper experimentally uses a neural network approach to analyze the disabled users' typing streams both in general and specific ways to identify their typing behaviors and subsequently, to make typing predictions and typing corrections. In this paper, a focused time-delay neural network (FTDNN) language model, a time gap model, a prediction model based on time gap, and a probabilistic neural network model (PNN) are developed. A 38% first hitting rate (HR) and a 53% first three HR in symbol prediction are obtained based on the analysis of a user's typing history through the FTDNN language modeling, while the modeling results using the time gap prediction model and the PNN model demonstrate that the correction rates lie predominantly in between 65% and 90% with the current testing samples, and 70% of all test scores above basic correction rates, respectively. The modeling process demonstrates that a neural network is a suitable and robust language modeling tool to analyze the noisy language stream. The research also paves the way for practical application development in areas such as informational analysis, text prediction, and error correction by providing a theoretical basis of neural network approaches for noisy language modeling. [ABSTRACT FROM AUTHOR]

This paper proposes a novel constructive training algorithm for cascade neural networks. By reformulating the cascade neural network as a linear-in-the-parameters model, we use the orthogonal least squares (OLS) method to derive a novel objective function for training new hidden units. With this objective function, the sum of squared errors (SSE) of the network can be maximally reduced after each new hidden unit is added, thus leading to a network with less hidden units and better generalization performance. Furthermore, the proposed algorithm considers both the input weights training and output weights training in an integrated framework, which greatly simplifies the training of output weights. The effectiveness of the proposed algorithm is demonstrated by simulation results. [ABSTRACT FROM PUBLISHER]

In this paper, the existence of oscillations for a type of recurrent neural network with time delays between neural interconnections is investigated. A new set of criteria is proposed to guarantee the existence of oscillations for a network model. The results are shown to be the generalization of some published works dealing with no delay systems. [ABSTRACT FROM PUBLISHER]

Different from gradient-based neural networks, a special kind of recurrent neural network (RNN) has recently been proposed by Zhang et al. for online matrix inversion. Such an RNN is designed based on a matrix-valued error function instead of a scalar-valued error function. In addition, it was depicted in an implicit dynamics instead of an explicit dynamics. In this paper, we develop and investigate a discrete-time model of Zhang neural network (termed as such and abbreviated as ZNN for presentation convenience), which is depicted by a system of difference equations. Comparing with Newton iteration for matrix inversion, we find that the discrete-time ZNN model incorporates Newton iteration as its special case. Noticing this relation, we perform numerical comparisons on different situations of using ZNN and Newton iteration for matrix inversion. Different kinds of activation functions and different step-size values are examined for superior convergence and better stability of ZNN. Numerical examples demonstrate the efficacy of both ZNN and Newton iteration for online matrix inversion. [ABSTRACT FROM AUTHOR]

This paper focuses on studying the H∞ and generalized H2 filtering problems for a class of delayed neural networks. The time-varying delay is only required to be continuous and bounded. Delay-dependent criteria are proposed such that the resulting filtering error system is globally exponentially stable with a guaranteed H∞ or generalized H2 performance. It is also shown that the designs of the desired filters are achieved by solving a set of linear matrix inequalities, which can be facilitated efficiently by resorting to standard numerical algorithms. It should be noted that, based on a novel bounding technique, several slack variables are introduced to reduce the conservatism of the derived conditions. Three examples with simulation results are provided to illustrate the effectiveness and performance of the developed approaches. [ABSTRACT FROM AUTHOR]

In this paper, a biologically inspired, CNN-based, multi-channel, texture boundary detection technique is presented. The proposed approach is similar to human vision system. The algorithm is simple and straightforward such that it can be implemented on the cellular neural networks (CNNs). CNN contains several important advantages, such as efficient real-time processing capability and feasible very large-scale integration (VLSI) implementation. The proposed algorithm also had been widely tested on synthetic texture images. Those texture images are randomly selected from the Brodatz textures database [1]. According to our simulation results, the boundaries of uniform textures can be detected quite successfully. For the nonuniform or nonregular textures, the results also indicate meaningful properties, and the properties also are consistent to the human visual sensation. The proposed algorithm also has been implemented on the CNN Universal Machine (CNN-UM), and yields similar results as the simulation on the PC. Based on the efficient performance of CNN-UM, the algorithm becomes very fast. [ABSTRACT FROM AUTHOR]

In this paper, we continue to explore application of nonsmooth analysis to the study of global asymptotic robust stability (GARS) of delayed neural networks. In combination with Lyapunov theory, our approach gives several new types of sufficient conditions ensuring GARS. A significant common aspect of our results is their low computational complexity. It is demonstrated that the reported results can be verified either by conducting spectral decompositions of symmetric matrices associated with the uncertainty sets of network parameters, or by solving a semidefinite programming problem. Nontrivial examples are constructed to compare with some closely related existing results. [ABSTRACT FROM AUTHOR]

In this paper, a new Lyapunov functional-based method is proposed for the stability analysis of delayed cellular neural networks (DCNN). Global exponential stability conditions are obtained for the general DCNN, the Hopfield neural networks (]INNs), and delayed HNNs with monotonic nondecreasing and nonconstant activation functions. [ABSTRACT FROM AUTHOR]

In this paper, the complete stability of cellular neural networks with time-varying delays is analyzed using the induction method and the contraction mapping principle. Delay-dependent and delay-independent conditions are obtained for locally stable equilibrium points to be located anywhere, which differ from the existing results on complete stability where the existence of equilibrium points in the saturation region is necessary for complete stability and locally stable equilibrium points can be in the saturation region only. In addition, some existing stability results in the literature are special cases of a new result herein. Simulation results are also discussed by use of two illustrative examples. [ABSTRACT FROM AUTHOR]

Blind source separation (BSS) aims at recovering statistically independent source signals from their linear mixtures without knowing the mixing coefficients. Besides independent component analysis, nonlinear principal component analysis (NPCA) is shown to be another useful tool for solving this problem, but it requires that the measured data be prewhitened. By taking into account the autocorrelation matrix of the measured data, we present in this paper a modified NPCA criterion, and develop a least-mean-square (LMS) algorithm and a recursive least-squares algorithm. They can perform the online BSS using directly the unwhitened observations. Since a natural gradient learning is applied and the prewhitening process is removed, the proposed algorithms work more efficiently than the existing NPCA algorithms, as verified by computer simulations on man-made sources as well as practical speech signals. [ABSTRACT FROM AUTHOR]

This paper investigates synchronization dynamics of a general model of complex delayed networks as well as the effects of time delays. Some simple yet generic criteria ensuring delay-independent and delay-dependent synchronization are derived, which are less conservative than those reported so far in the literature. Moreover, a scale ‘v’ denoted by a function of the smallest and the second largest eigenvalues of coupling matrix is presented to analyze the effects of time delays on synchronization of the networks. Furthermore, various kinds of coupling schemes, including small-world networks and scale-free networks, are studied. It is shown that, if the coupling delays are less than a positive threshold, then the network will be synchronized. On the other hand, with the increase of the coupling delays, the synchronizability of the network will be restrained and even eventually desynchronized. The results are illustrated by a prototype composed of the chaotic Duffing oscillators. Numerical simulations are also given to verify theoretical results. [ABSTRACT FROM AUTHOR]

Overfitting has long been recognized as a problem endemic to models with a large number of parameters. The usual method of avoiding this problem in neural networks is to avoid fitting the data too precisely, and this technique cannot determine the exact model size directly. In this paper, we describe an alternative, information theoretic criterion to determine the number of neurons in the optimal model. When applied to the time series prediction problem we find that models which minimize the description length (DL) of the data, both generalize well and accurately capture the underlying dynamics. We illustrate our method with several computational and experimental examples. [ABSTRACT FROM AUTHOR]

In this paper, we develop an advanced architecture and come up with a comprehensive design methodology of genetically optimized hybrid fuzzy neural networks (gHFNNs). The construction of gHFNN exploits fundamental technologies of computational intelligence (CI), namely fuzzy sets, neural networks, and genetic algorithms (GAs). The architecture of the gHFNN results from a highly synergistic usage of the genetic optimization-driven hybrid system being generated by combining fuzzy neural networks (FNNs) with polynomial neural networks (PNN). FNN contributes to the formation of the premise part of the overall network structure of the gHFNN. The consequence part of the gHFNN is designed using PNNs. The optimization of the FNN is realized with the aid of a standard backpropagation learning algorithm and genetic optimization. As the consequence part of the gHFNN, the development of the PNN dwells on two general optimization mechanisms: the structural optimization is realized via GAs whereas in the case of the parametric optimization we proceed with a standard least square method-based learning (optimization). Through the consecutive process of such structural and parametric optimization, an optimized PNN becomes generated in a dynamic fashion. To evaluate the performance of the gHFNNs, we experimented with a number of representative numerical examples. A comparative analysis demonstrates that the proposed gHFNNs are neurofuzzy systems with higher accuracy as well as more superb predictive capability than other models available in the literature. [ABSTRACT FROM AUTHOR]