Search

This brief considers a class of delayed full-range (FR) cellular neural networks (CNNs) with uncertain interconnections between neurons modeled by means of intervalized matrices. Using mathematical tools from the theory of differential inclusions, a fundamental result on global robust stability of standard (S) CNNs is extended to prove global robust exponential stability for the corresponding class (same interconnection weights and inputs) of FR-CNNs. The result is of theoretical interest since, in general, the equivalence between the dynamical behavior of FR-CNNs and S-CNNs is not guaranteed.

This paper presents the Visual Attention Engine (VAE), which is a digital cellular neural network (CNN) that executes the VA algorithm to speed up object-recognition. The proposed time-multiplexed processing element (TMPE) CNN topology achieves high performance and small area by integrating 4800 (8060) cells and 120 PEs. Pipelined operation of the PEs and single-cycle global shift capability of the cells result in a high PE utilization ratio of 93%. The cells are implemented by 6T static random access memory-based register files and dynamic shift registers to enable a small area of 4.5 . The bus connections between PEs and cells are optimized to minimize power consumption. The VAE is integrated within an object-recognition system-on-chip (SoC) fabricated in the 0.13- complementary metal-oxide-semiconductor process. It achieves 24 GOPS peak performance and 22 GOPS sustained performance at 200 MHz enabling one CNN iteration on an 8060 pixel image to be completed in just 4.3 . With VA enabled using the VAE, the workload of the object-recognition SoC is significantly reduced, resulting in 83% higher frame rate while consuming 45% less energy per frame without degradation of recognition accuracy.

In this brief, a convolutional learning system for classification of segmented objects represented in 3-D as point clouds of laser reflections is proposed. Several novelties are discussed: (1) extension of the existing convolutional neural network (CNN) framework to direct processing of 3-D data in a multiview setting which may be helpful for rotation-invariant consideration, (2) improvement of CNN training effectiveness by employing a stochastic meta-descent (SMD) method, and (3) combination of unsupervised and supervised training for enhanced performance of CNN. CNN performance is illustrated on a two-class data set of objects in a segmented outdoor environment.

The Adachi neural network (AdNN) is a fascinating neural network (NN) which has been shown to possess chaotic properties, and to also demonstrate associative memory (AM) and pattern recognition (PR) characteristics. Variants of the AdNN have also been used to obtain other PR phenomena, and even blurring. An unsurmountable problem associated with the AdNN and the variants referred to above is that all of them require a quadratic number of computations. This is essentially because the NNs in each case are completely connected graphs. In this paper, we consider how the computations can be significantly reduced by merely using a linear number of computations. To achieves this, we extract from the original completely connected graph one of its spanning trees. We then address the problem of computing the weights for this spanning tree. This is done in such a manner that the modified tree-based NN has approximately the same input-output characteristics, and thus the new weights are themselves calculated using a gradient-based algorithm. By a detailed experimental analysis, we show that the new linear-time AdNN-like network possesses chaotic and PR properties for different settings. As far as we know, such a tree-based AdNN has not been reported, and the results given here are novel.

In this paper, a delayed projection neural network is proposed for solving a class of linear variational inequality problems. The theoretical analysis shows that the proposed neural network is globally exponentially stable under different conditions. By the proposed linear matrix inequality (LMI) method, the monotonicity assumption on the linear variational inequality is no longer necessary. By employing Lagrange multipliers, the proposed method can resolve the constrained quadratic programming problems. Finally, simulation examples are given to demonstrate the satisfactory performance of the proposed neural network.

The K-nearest neighbor (KNN) rule is one of the most widely used pattern classification algorithms. For large data sets, the computational demands for classifying patterns using KNN can be prohibitive. A way to alleviate this problem is through the condensing approach. This means we remove patterns that are more of a computational burden but do not contribute to better classification accuracy. In this brief, we propose a new condensing algorithm. The proposed idea is based on defining the so-called chain. This is a sequence of nearest neighbors from alternating classes. We make the point that patterns further down the chain are close to the classification boundary and based on that we set a cutoff for the patterns we keep in the training set. Experiments show that the proposed approach effectively reduces the number of prototypes while maintaining the same level of classification accuracy as the traditional KNN. Moreover, it is a simple and a fast condensing algorithm.

The notion of counterclockwise (ccw) input-output (I-O) dynamics, introduced by Angeli (2006) to deal with questions of multistability in interconnected dynamical systems, is applied and further developed in order to analyze convergence and stability of neural networks. By pursuing a modular approach, we interpret a cellular nonlinear network (CNN) as a positive feedback of a parallel block of single-input-single-output (SISO) dynamical systems, the neurons, and a static multiple-input-multiple-output (MIMO) system that couples them (typically the so-called interconnection matrix). The analysis extends previously known results by enlarging the class of allowed neural dynamics to higher order neurons.

To provide an ability to characterize local features for the chaotic neural network (CNN), Gauss wavelet is used for the self-feedback of the CNN with the dilation parameter acting as the bifurcation parameter. The exponentially decaying dilation parameter and the chaotically varying translation parameter not only govern the wavelet self-feedback transform but also enable the CNN to generate complex dynamics behavior preventing the network from being trapped in the local minima. Analysis of the energy function of the CNN indicates that the local characterization ability of the proposed CNN is effectively provided by the wavelet self-feedback in the manner of inverse wavelet transform and that the proposed CNN can achieve asymptotical stability. The experimental results on traveling salesman problem (TSP) suggest that the proposed CNN has a higher average success rate for obtaining globally optimal or near-optimal solutions.

Cellular simultaneous recurrent neural network (SRN) has been shown to be a function approximator more powerful than the multilayer perceptron (MLP). This means that the complexity of MLP would be prohibitively large for some problems while SRN could realize the desired mapping with acceptable computational constraints. The speed of training of complex recurrent networks is crucial to their successful application. This work improves the previous results by training the network with extended Kalman filter (EKF). We implemented a generic cellular SRN (CSRN) and applied it for solving two challenging problems: 2-D maze navigation and a subset of the connectedness problem. The speed of convergence has been improved by several orders of magnitude in comparison with the earlier results in the case of maze navigation, and superior generalization has been demonstrated in the case of connectedness. The implications of this improvements are discussed.

A new criterion for the global asymptotic stability of the equilibrium point of cellular neural networks with multiple time delays is presented. The obtained result possesses the structure of a linear matrix inequality and can be solved efficiently using the recently developed interior-point algorithm. A numerical example is used to show the effectiveness of the obtained result.

Recurrent neural networks have interesting properties and can handle dynamic information processing unlike ordinary feedforward neural networks. However, they are generally difficult to use because there is no convenient learning scheme. In this paper, a recursive learning scheme for recurrent neural networks using the simultaneous perturbation method is described. The detailed procedure of the scheme for recurrent neural networks is explained. Unlike ordinary correlation learning, this method is applicable to analog learning and the learning of oscillatory solutions of recurrent neural networks. Moreover, as a typical example of recurrent neural networks, we consider the hardware implementation of Hopfield neural networks using a field-programmable gate array (FPGA). The details of the implementation are described. Two examples of a Hopfield neural network system for analog and oscillatory targets are shown. These results show that the learning scheme proposed here is feasible.

In a recent work, a new method has been introduced to analyze complete stability of the standard symmetric cellular neural networks (CNNs), which are characterized by local interconnections and neuron activations modeled by a three-segment piecewise-linear (PWL) function. By complete stability it is meant that each trajectory of the neural network converges toward an equilibrium point. The goal of this paper is to extend that method in order to address complete stability of the much wider class of symmetric neural networks with an additive interconnecting structure where the neuron activations are general PWL functions with an arbitrary number of straight segments. The main result obtained is that complete stability holds for any choice of the parameters within the class of symmetric additive neural networks with PWL neuron activations, i.e., such a class of neural networks enjoys the important property of absolute stability of global pattern formation. It is worth pointing out that complete stability is proved for generic situations where the neural network has finitely many (isolated) equilibrium points, as well as for degenerate situations where there are infinite (nonisolated) equilibrium points. The extension in this paper is of practical importance since it includes neural networks useful to solve significant signal processing tasks (e.g., neural networks with multilevel neuron activations). It is of theoretical interest too, due to the possibility of approximating any continuous function (e.g., a sigmoidal function), using PWL functions. The results in this paper confirm the advantages of the method of Forti and Tesi, with respect to LaSalle approach, to address complete stability of PWL neural networks.

This paper introduces a novel neural architecture which is capable of similar performance to any of the "classic" neural paradigms while having a very simple and efficient mixed-signal implementation which makes it a valuable candidate for intelligent signal processing in portable multimedia applications. The architecture and its realization circuit are described and the functional capabilities of the novel neural architecture called a simplicial neural cell are demonstrated for both regression and classification problems including nonlinear image filtering.

In this paper, a sufficient condition related to the existence of a unique equilibrium point and its global asymptotic stability for cellular network networks with delay (DCNNs) is derived. It is shown that the condition relies on the feedback matrices and is independent of the delay parameter. Furthermore, this condition is less restrictive than that given in the literature.

Estimate of exponential convergence rate and exponential stability are studied for a class of neural networks which includes the Hopfield neural networks and the cellular neural networks. Both local and global exponential convergence is discussed. Theorems for estimate of exponential convergence rate are established and the bounds on the rate of convergence are given. The domains of attraction in the case of local exponential convergence are obtained. Simple conditions are presented for checking exponential stability of the neural networks.

The solution of the nonlinear servomechanism problem relies on the solvability of a set of mixed nonlinear partial differential and algebraic equations known as the regulator equations. Due to the nonlinear nature, it is difficult to obtain the exact solution of the regulator equations. This paper proposes to solve the regulator equations based on a class of recurrent neural network, which has the features of a cellular neural network. This research not only represents a novel application of the neural networks to numerical mathematics, but also leads to an effective approach to approximately solving the nonlinear servomechanism problem. The resulting design method is illustrated by application to the well-known ball and beam system.

A new continuum model complementary to traditional cellular neural networks is introduced in this note. We consider a cellular neural field formed by infinitely many cellular neurons and modelled by an integrodifferential equation. Then, using LaSalle's invariance principle on Banach space, we show that the field quantity will asymptotically converge to an equilibrium state under the condition that all equilibria of the system are isolated. From the practical sense, the convergence indicates the essential capability of retrieving message from original raw data

A new Lyapunov-Krasovskii functional is constructed for delayed cellular neural networks, and the S-procedure is employed to handle the nonlinearities. An improved global asymptotic stability criterion is also derived that is a generalization of, and an improvement over, previous results. Numerical examples demonstrate the effectiveness of the criterion.

The use of a current-mode pulse width modulation (CM-PWM) technique to implement analog artificial neural networks (ANNs) is presented. This technique can be used to efficiently implement the weighted summation operation (WSO) that are required in the realization of a general ANN. The sigmoidal transformation is inherently performed by the nonlinear transconductance amplifier, which is a key component in the current integrator used in the realization of WSO. The CM-PWM implementation results in a minimum silicon area, and therefore is suitable for very large scale neural systems. Other pronounced features of the CM-PWM implementation are its easy programmability, electronically adjustable gains of neurons, and modular structures. In this paper, all the current-mode CMOS circuits (building blocks) required for the realization of CM-PWM ANNs are presented and simulated. Four modules for modular design of ANNs are introduced. Also, it is shown that the CM-PWM technique is an efficient method for implementing discrete-time cellular neural networks (DT-CNNs). Two application examples are given: a winner-take-all circuit and a connected component detector.

An engineering annealing method for optimal solutions of cellular neural networks is presented. Cellular neural networks are very promising in solving many scientific problems in image processing, pattern recognition, and optimization by the use of stored program with predetermined templates. Hardware annealing, which is a paralleled version of mean-field annealing in analog networks, is a highly efficient method of finding optimal solutions of cellular neural networks. It does not require any stochastic procedure and henceforth can be very fast. The generalized energy function of the network is first increased by reducing the voltage gain of each neuron. Then, the hardware annealing searches for the globally minimum energy state by continuously increasing the gain of neurons. The process of global optimization by the proposed annealing can be described by the eigenvalue problems in the time-varying dynamic system. In typical nonoptimization problems, it also provides enough stimulation to frozen neurons caused by ill-conditioned initial states.

When low-level hardware simulations of cellular neural networks (CNNs) are very costly for exploring new applications, the use of a behavioral simulator becomes indispensable. This paper presents a software prototype capable of performing image processing applications using CNNs. The software is based on a CNN multilayer structure in which each primary color is assigned to a unique layer. This allows an added flexibility as different processing applications can be performed in parallel. To be able to handle a full range of color tones, two novel color mapping schemes were derived. In the proposed schemes the color information is obtained from the cell's state rather than from its output. This modification is necessary because for many templates CNN has only binary stable outputs from which only either a fully saturated or a black color can be obtained. Additionally, a postprocessor capable of performing pixelwise logical operations among color layers was developed to enhance the results obtained from CNN. Examples in the areas of medical image processing, image restoration, and weather forecasting are provided to demonstrate the robustness of the software and the vast potential of CNN.

In this paper, we investigate the cluster synchronization problem for linearly coupled networks, which can be recurrently connected neural networks, cellular neural networks, Hodgkin-Huxley models, Lorenz chaotic oscillators, etc., by adding some simple intermittent pinning controls. We assume the nodes in the network to be identical and the coupling matrix to be asymmetric. Some sufficient conditions to guarantee global cluster synchronization are presented. Furthermore, a centralized adaptive intermittent control is introduced and theoretical analysis is provided. Then, by applying the adaptive approach on the diagonal submatrices of the asymmetric coupling matrix, we also get the corresponding cluster synchronization result. Finally, numerical simulations are given to verify the theoretical results.

In this brief, the problems of delay-dependent stability analysis and strict (Q,S,ℜ)-α-dissipativity analysis are investigated for cellular neural networks (CNNs) with distributed delay. First, by introducing an integral partitioning technique, two new forms of Lyapunov-Krasovskii functionals are constructed, and improved distributed delay-dependent stability conditions are established in terms of linear matrix inequalities. Based on this criterion, a new sufficient delay and α-dependent condition is given to guarantee that the CNNs with distributed delay are strictly (Q,S,ℜ)-α-dissipative. The results developed in this brief can tolerate larger allowable delay than existing ones in the literature, which is demonstrated by several examples.

In this paper, we study the distribution of attraction basins of multiple equilibrium points of cellular neural networks (CNNs). Under several conditions, the boundaries of the attracting basins of the stable equilibria of a completely stable CNN system are composed of the closures of the stable manifolds of unstable equilibria of (n - 1) dimensions. As demonstrations of this idea, under the conditions proposed in the literature which depicts stable and unstable equilibria, we identify the attraction basin of each stable equilibrium of which the boundary is composed of the stable manifolds of the unstable equilibria precisely. We also investigate the attracting basins of a simple class of symmetric 1-D CNNs via identifying the unstable equilibria of which the stable manifold is (n - 1) dimensional and the completely stable asymmetric CNNs with stable equilibria less than 2(n).

This brief studies exponential H(infinity) synchronization of a class of general discrete-time chaotic neural networks with external disturbance. On the basis of the drive-response concept and H(infinity) control theory, and using Lyapunov-Krasovskii (or Lyapunov) functional, state feedback controllers are established to not only guarantee exponential stable synchronization between two general chaotic neural networks with or without time delays, but also reduce the effect of external disturbance on the synchronization error to a minimal H(infinity) norm constraint. The proposed controllers can be obtained by solving the convex optimization problems represented by linear matrix inequalities. Most discrete-time chaotic systems with or without time delays, such as Hopfield neural networks, cellular neural networks, bidirectional associative memory networks, recurrent multilayer perceptrons, Cohen-Grossberg neural networks, Chua's circuits, etc., can be transformed into this general chaotic neural network to be H(infinity) synchronization controller designed in a unified way. Finally, some illustrated examples with their simulations have been utilized to demonstrate the effectiveness of the proposed methods.

The paper considers a general neural network model with impulses at a given sequence of instants, discontinuous neuron activations, delays, and time-varying data and inputs. It is shown that when the neuron interconnections satisfy an M-matrix condition, or a dominance condition, then the state solutions and the output solutions display a common asymptotic behavior as time t--+infinity. It is also shown, via a new technique based on prolonging the solutions of the delayed neural network to -infinity, that it is possible to select a unique special solution that is globally exponentially stable and can be considered as the unique global attractor for the network. Finally, this paper shows that for almost periodic data and inputs the selected solution is almost periodic; moreover, it is robust with respect to a large class of perturbations of the data. Analogous results also hold for periodic data and inputs. A by-product of the analysis is that a sequence of almost periodic impulses is able to induce in the generic case (nonstationary) almost periodic solutions in an otherwise globally convergent nonimpulsive neural network. To the authors' knowledge the results in this paper are the only available results on global exponential stability of the unique periodic or almost periodic solution for a general neural network model combining three main features, i.e., impulses, discontinuous neuron activations and delays. The results in this paper are compared with several results in the literature dealing with periodicity or almost periodicity of some subclasses of the neural network model here considered and some hints for future work are given.

This paper presents new complete stability results for delayed cellular neural networks (DCNNs). A novel method is proposed for complete stability analysis of DCNNs. By applying the M-matrix theory and introducing some new estimation techniques on the solutions of DCNNs, a simple and improved complete stability criterion is derived. The new criterion unifies the delay-dependent and delay-independent complete stability conditions for DCNNs. Moreover, the obtained delay-dependent criterion can give a larger upper bound of the time delay than the existing ones such that the complete stability can still be retained. Numerical examples are presented which show that the new complete stability results for DCNNs are compared favorably with the existing results.

A stability analysis is performed for the brain-state-in-a-box (BSB) neural models with weight matrices that need not be symmetric. The implementation of associative memories using the analyzed class of neural models is also addressed. In particular, the authors modify the BSB model so that they can better control the extent of the domains of attraction of stored patterns. Generalizations of the results obtained for the BSB models to a class of cellular neural networks are also discussed. >

In this brief, a synthesis procedure for cellular neural networks (CNNs) with space-invariant cloning templates is proposed. The design algorithm is based on the use of the evolutionary algorithm of the particle swarm optimization (PSO) with the application to associative memories. The proposed synthesis procedure takes into account requirements in terms of robustness to parametric variations. Numerical results show that the networks also guarantee good performances in terms of correct recall in the presence of noisy patterns.

In this paper, global synchronization of linearly coupled neural network (NN) systems with time-varying coupling is investigated. The dynamical behavior of the uncoupled system at each node is general, which can be chaotic or others; the coupling configuration is time varying, i.e., the coupling matrix is not a constant matrix. Based on Lyapunov function method and the specific property of Householder transform, some criteria for the global synchronization are obtained. By these criteria, one can verify whether the coupled system with time-varying coupling is globally synchronized, which is important and useful for both understanding and interpreting synchronization phenomena and designing coupling configuration. Finally, two simulations are given to demonstrate the effectiveness of the theoretical results.

In this study, we present the initial results of cellular neural network (CNN)-based autowave metric to high-speed pattern recognition of gray-scale images. the application is to a problem involving separation of metallic wear debris particles from air bubbles. This problem arises in an optical-based system for determination of mechanical wear. This paper focuses on distinguishing debris particles suspended in the oil flow from air bubbles and aims to employ CNN technology to create an online fault monitoring system. For the class of engines of interest bubbles occur much more often than debris particles and the goal is to develop a classification system with an extremely low false alarm rate for misclassified bubbles. The designed analogic CNN algorithm detects and classifies single bubbles es and bubble groups using binary morphology and autowave metric. The debris particles are separated based on autowave distances computed between bubble models and the unknown objects. Initial experiments indicate that the proposed algorithm is robust and noise tolerant and when implemented on a CNN universal chip it provides a solution in real time.

In this paper, we present a neural-networks-based knowledge discovery and data mining (KDDM) methodology based on granular computing, neural computing, fuzzy computing, linguistic computing, and pattern recognition. The major issues include 1) how to make neural networks process both numerical and linguistic data in a data base, 2) how to convert fuzzy linguistic data into related numerical features, 3) how to use neural networks to do numerical-linguistic data fusion, 4) how to use neural networks to discover granular knowledge from numerical-linguistic data bases, and 5) how to use discovered granular knowledge to predict missing data. In order to answer the above concerns, a granular neural network (GNN) is designed to deal with numerical-linguistic data fusion and granular knowledge discovery in numerical-linguistic databases. From a data granulation point of view, the GNN can process granular data in a database. From a data fusion point of view, the GNN makes decisions based on different kinds of granular data. From a KDDM point of view, the GNN is able to learn internal granular relations between numerical-linguistic inputs and outputs, and predict new relations in a database. The GNN is also capable of greatly compressing low-level granular data to high-level granular knowledge with some compression error and a data compression rate. To do KDDM in huge data bases, parallel GNN and distributed GNN will be investigated in the future.

In this paper, a very large scale integration chip of an analog image weighted-order statistic (WOS) filter based on cellular neural network (CNN) architecture for real-time applications is described. The chip has been implemented in CMOS AMS 0.8 /spl mu/m technology. CNN-based filter consists of feedforward nonlinear template B operating within the window of 3 /spl times/ 3 pixels around the central pixel being filtered. The feedforward nonlinear CNN coefficients have been realized using programmable nonlinear coupler circuits. The WOS filter chip allows for processing of images with 300 pixels horizontal resolution. The resolution can be increased by cascading of the chips. Experimental results of basic circuit building blocks measurements are presented. Functional tests of the chip have been performed using a special test setup for PAL composite video signal processing. Using the setup real images have been filtered by WOS filter chip under test.

In this paper, a new sufficient condition is given for the uniqueness and global asymptotic stability of the equilibrium point for delayed cellular neural networks (DCNNs). This condition imposes constraints on the feedback and delayed feedback matrices of a DCNN independently of the delay parameter. This result is also compared with the previous results derived in the literature.

In a previous work, the authors proposed an analog Hopfield-type neural network that identified the K largest components of a list of real numbers. In this work, we identify computable restrictions on the parameters, in order that the network can repeatedly process lists, one after the other, at a given rate. A complete mathematical analysis gives analytical bounds for the time required in terms of circuit parameters, the length of the lists, and the relative separation of list elements. This allows practical setting of circuit parameters for required clocking times. The emphasis is on high gain functioning of each neuron. Numerical investigations show the accuracy of the theoretical predictions, and study the influence of various parameters on performance.

The sensitivity of the global error (cost) function to the inclusion/exclusion of each synapse in the artificial neural network is estimated. Introduced are shadow arrays which keep track of the incremental changes to the synaptic weights during a single pass of back-propagating learning. The synapses are then ordered by decreasing sensitivity numbers so that the network can be efficiently pruned by discarding the last items of the sorted list. Unlike previous approaches, this simple procedure does not require a modification of the cost function, does not interfere with the learning process, and demands a negligible computational overhead. >

By exponential dichotomy about differential equations, a formal almost periodic solution (APS) of a class of cellular neural networks (CNNs) with distributed delays is obtained. Then, within different normed spaces, several sufficient conditions guaranteeing the existence and uniqueness of an APS are proposed using two fixed-point theorems. Based on the continuity property and some inequality techniques, two theorems insuring the global stability of the unique APS are given. Comparing with known literatures, all conclusions are drawn with slacker restrictions, e.g., do not require the integral of the kernel function determining the distributed delays from zero to positive infinity to be one, and the activation functions to be bounded, etc.; besides, all criteria are obtained by different ways. Finally, two illustrative examples show the validity and that all criteria are easy to check and apply.

In this paper, the multiperiodicity of a general class of discrete-time delayed neural networks (DTDNNs) is formulated and studied. Several sufficient conditions are obtained to ensure n-neuron DTDNNs can have 2n periodic orbits and these periodic orbits are locally attractive. In addition, we give the conditions for a periodic orbit to be locally or globally attractive when the periodic orbit locates in a designated region. As two typical representatives, the Hopfield neural network and the cellular neural network are examined in detail. These conditions improve and extend the existing stability results in the literature. Simulations results are also discussed in three illustrative examples.

This paper presents new theoretical results on global exponential stability of recurrent neural networks with bounded activation functions and time-varying delays. The stability conditions depend on external inputs, connection weights, and time delays of recurrent neural networks. Using these results, the global exponential stability of recurrent neural networks can be derived, and the estimated location of the equilibrium point can be obtained. As typical representatives, the Hopfield neural network (HNN) and the cellular neural network (CNN) are examined in detail.

Without assuming boundedness and differentiability of the activation functions and any symmetry of interconnections, we employ Lyapunov functions to establish some sufficient conditions ensuring existence, uniqueness, global asymptotic stability, and even global exponential stability of equilibria for the Cohen-Grossberg neural networks with and without delays. Our results are not only presented in terms of system parameters and can be easily verified and also less restrictive than previously known criteria and can be applied to neural networks, including Hopfield neural networks, bidirectional association memory neural networks, and cellular neural networks.

In this paper, we study cellular neural networks with almost periodic variable coefficients and time-varying delays. By using the existence theorem of almost periodic solution for general functional differential equations, introducing many real parameters and applying the Lyapunov functional method and the technique of Young inequality, we obtain some sufficient conditions to ensure the existence, uniqueness, and global exponential stability of almost periodic solution. The results obtained in this paper are new, useful, and extend and improve the existing ones in previous literature.

A novel linear matrix inequality (LMI)-based criterion for the global asymptotic stability and uniqueness of the equilibrium point of a class of delayed cellular neural networks (CNNs) is presented. The criterion turns out to be a generalization and improvement over some previous criteria.

A description is given of 11 papers from the April 1990 special issue on neural networks in control systems of IEEE Control Systems Magazine. The emphasis was on presenting as varied and current a picture as possible of the use of neural networks in control. The papers described cover: the design of associative memories using feedback neural networks; a method to use neural networks to control highly nonlinear systems; the modeling of nonlinear chemical systems using neural networks; the identification of dynamical systems; the comparison of conventional adaptive controllers and neural-network-based controllers; a method to provide adaptive control for nonlinear systems; neural networks and back-propagation; the back-propagation algorithm; the use of trained neural networks to regulate the pitch attitude of an underwater telerobot; the control of mobile robots; and the issues involved in integrating neural networks and knowledge-based systems. >

In this letter, we point out that the linear matrix inequality (LMI)-based criterion obtained in the above paper (Singh, IEEE Trans. Neural Netw., vol. 15, no. 1, p. 223-5, 2004) for the global exponential stability of the delayed neural networks can be simplified to a simpler but equivalent form and, thus, show that it is not necessary to have such complex form of condition in the above paper. As a result, we also answer the question raised by the author of the above paper.

Two ANNA neural-network chips are integrated on a 6U VME board, to serve as a high-speed platform for a wide variety of algorithms used in neural-network applications as well as in image analysis. The system can implement neural networks of variable sizes and architectures, but can also be used for filtering and feature extraction tasks that are based on convolutions. The board contains a controller implemented with field programmable gate arrays (FPGA's), memory, and bus interfaces, all designed to support the high compute power of the ANNA chips. This new system is designed for maximum speed and is roughly 10 times faster than a previous board. The system has been tested for such tasks as text location, character recognition, and noise removal as well as for emulating cellular neural networks (CNN's). A sustained speed of up to two billion connections per second (GC/s) and a recognition speed of 1000 characters per second has been measured.

A performance analysis is presented that focuses on the achievable speedup of a neural network implementation and on the optimal size of a processor network (transputers or multicomputers that communicate in a comparable manner). For fully and randomly connected neural networks the topology of the processor network can only have a small, constant effect on the iteration time. With randomly connected neural networks, even severely limiting node fan-in has only a negligible effect on decreasing the communication overhead. The class of modular neural networks is studied as a separate case which is shown to have better implementation characteristics. On the basis of implementation constraints, it is argued that randomly connected neural networks cannot be realistic models of the brain. >

The design of fully connected discrete-time neural networks, with threshold units, can be performed by solving a set of linear inequalities. Using this formulation, the design problem can be handled by several powerful algorithms. This approach is extended to the design of continuous-time neural networks with sigmoidal units, which represent a more realistic model of analog circuit implementations. The proposed method is based on some theoretical results proved in this paper. >