Search

Fully memristive neuron learning framework, which uses drift and diffusion memristor models to build an artificial neuron structure, becomes a hot topic recently with the development of memristor. However, some other devices like resistor or capacitor are still necessary in recent works of fully memristive learning framework. Theoretically, if one neuron is built by memristors only, the technique process will be simpler and learning framework will be more like biological brain. In this paper, a fully memristive spiking-neuron learning framework is introduced, in which a neuron structure is just built of one drift and one diffusion memristive models and spikes are used as transmission signals. The learning framework and spiking coding mode are simple and direct without any complicated calculation on hardware. To verify its merits, a feedforward neural network for pattern recognition and a cellular neural network for edge detection are designed. Experimental results show that compared to other memristive neural networks, processing speed of the proposed framework is very high, and the hardware resource is saved in pattern recognition. Further, due to the dynamic filtering function of diffusion memristor model in our learning framework, its peak signal noise ratio (PSNR) is much higher than traditional algorithms in edge detection. [ABSTRACT FROM AUTHOR]

• Topographic architectures enable fast detection of hierarchical layers. • Detection of hierarchical layers is carried out by morphological operations. • Grouping is simplified to the diffusion template of Cellular Neural Networks. • Real-time processing is achieved when implementing on topographic architectures. Information patterns are ubiquitous and their automatic detection is fundamental in many computer vision tasks. Robust and fast detection of object candidates is essential as well as the ability to adapt the system to new situations. We propose a general, task independent method that i) locates interesting patterns on binary images by creating a hierarchical layered structure based on neighborhood topography of connected components, and ii) identifies object groups applying saliency principles. Saliency values are assigned to both object groups and individuals, that can be referred as a priority queue of image regions, or alternatively a proposal for blob processing order. Empirical analysis through several computer vision examples is provided including applications for blind and visually impaired people. The proposed algorithm can be efficiently implemented on processor arrays, since it mostly contains standard topographic instructions, and we also introduce a real-time implementation on the Eye-RIS/Toshiba SPS vision system. [ABSTRACT FROM AUTHOR]

• An improved Cellular Neural Network (CellNN) by local-neighbor binary constraints. • A feature extraction framework based on the state and output feature maps from recurrent CellNN convolutions. • A feature map compression, joint-distribution pattern fusion and a multi-resolution scheme optimized by softmax. Texture recognition is one of the most important branches in image research. This paper mainly aims to develop a new solution to address texture recognition using a Cellular Neural Network (CellNN). Firstly, it proposes an improved model of CellNN by the binary constraints of local receptive fields, and then designs a recurrent convolution framework of such a model to generate two types of texture feature maps, including state feature maps and output feature maps. In order to obtain low-dimensional features, state feature maps are further compressed by the mapping of rotation-invariant patterns and the merging of low-frequency occurrence patterns. By the statistics of joint-distribution patterns, state feature maps and output feature maps are fused together to generate the features of single resolution. Moreover, a multi-resolution feature combination scheme is also designed by the optimization of softmax & variance and concatenation of multiple features. Finally, a fully-connected neural network is trained to work as a texture recognizer. The experimental comparisons of totally 15 algorithms on five benchmark datasets show that, on the dataset whose texture-class quantity is not beyond 30, such as Brodatz, our method could always acquire the highest recognition accuracy, outperforming any other compared ones. On the big dataset with huge texture-class quantity, such as ALOT, our method could also surpass any other non-deep-learning one, such as the state-of-the-art gLBP, only slightly falling behind the best two deep-learning ones, FV-Alex and FV-VGGVD. However, in terms of time cost, our method could always outperform any deep-learning one in feature extraction stage, and also surpass any compared one except original LBP in feature matching. [ABSTRACT FROM AUTHOR]

In texture classification, local binary pattern (LBP) is currently one of the most widely-concerned feature encoding models. Most existing LBP-based texture classification methods are usually limited to single-kind texture features. In fact, an across-domain fusion of LBP features with other features, such as image contours, could be another potential path to promote texture classification. To enhance the feature modeling ability of LBP-based methods, this paper firstly designs a Cellular Neural Network (CellNN) with recurrent convolutions, initially trained by a simplified simulated-annealing algorithm, to extract informative image contours. For better reliability, a new three-channel contour extractor of deep CellNNs (i. e. , dCellNNs) is proposed. This extractor contains the initially-trained CellNNs of more than three layers, and it is further optimized by fine-tuning parameters. Moreover, a new weighted-base algorithm is designed to fulfill the fusion of the multi-scale texture features by LBPs and the contour features by dCellNNs to enhance feature representation. Finally, these enhanced features are concatenated together to generate the final multi-scale features of given texture image. On texture datasets KTH, Brodatz, OTC12 and UIUC, experiment results verify that the across-domain fusion of multi-scale LBPs and dCellNNs is efficient in capturing & enhancing texture features. With moderate feature dimensionality and computational costs, it could improve texture classification, acquiring an obvious accuracy increase on previous state-of-the-art ones, e.g. , a rise of 2.58% on KTH-TIPS2b, a rise of 3.11% on Brodatz, a rise of 0.71% on OTC12 and a rise of 0.42% on UIUC. • A multi-scale across-domain feature fusion of textures and contours is proposed. • The first deep model of CellNN (dCellNNs) with two-stage training is proposed. • The three-channel texture contour extractor of dCellNNs is designed. • A weighted-base fusing is designed for the across-domain fusion of features. [ABSTRACT FROM AUTHOR]

This paper presents a new neural network methodology for modelling of soft tissue deformation for surgical simulation. The proposed methodology formulates soft tissue deformation and its dynamics as the neural propagation and dynamics of cellular neural networks for real-time, realistic, and stable simulation of soft tissue deformation. It develops two cellular neural network models; based on the bioelectric propagation of biological tissues and principles of continuum mechanics, one cellular neural network model is developed for propagation and distribution of mechanical load in soft tissues; based on non-rigid mechanics of motion in continuum mechanics, the other cellular neural network model is developed for governing model dynamics of soft tissue deformation. The proposed methodology not only has computational advantage due to the collective and simultaneous activities of neural cells to satisfy the real-time computational requirement of surgical simulation, but also it achieves physical realism of soft tissue deformation according to the bioelectric propagation manner of mechanical load via dynamic neural activities. Furthermore, the proposed methodology also provides stable model dynamics for soft tissue deformation via the nonlinear property of the cellular neural network. Interactive soft tissue deformation with haptic feedback is achieved via a haptic device. Simulations and experimental results show the proposed methodology exhibits the nonlinear force-displacement relationship and associated nonlinear deformation of soft tissues. Furthermore, not only isotropic and homogeneous but also anisotropic and heterogeneous materials can be modelled via a simple modification of electrical conductivity values of mass points. [ABSTRACT FROM AUTHOR]

A general solution for the construction of Cellular Neural Network (CNN) weights (cloning template) with Random Weight Change (RWC) algorithm is proposed. A target image for each input image is prepared via a sketch or any other kind of image processing technique for learning of Cellular Neural Network templates. A vector of randomly generated small values is added to the original weights and tested upon the input-target image pair. As a result, if the learning error decreases, the weight is taken for learning in the next iteration and updated using the same vector of random values. Otherwise, a new random vector for updating the weights is regenerated. One of the strong benefits of the proposed weight learning method is the simplicity of its learning algorithm and hence a simpler hardware architecture. Moreover the proposed method provides a unified solution to the problem of learning CNN templates without having to modify the original CNN structure and is applicable for all types of CNNs and input images. Successful learning of templates for various image processing tasks using different CNN structures are also demonstrated in this paper. [ABSTRACT FROM AUTHOR]

The brain connections in the different regions demonstrate the characteristics of brain activities. In addition, in various conditions and with neuropsychological disorders, the brain has special patterns in different regions. This paper presents a model to show and compare the connection patterns in different brain regions of children with autism (53 boys and 36 girls) and control children (61 boys and 33 girls). The model is designed by cellular neural networks and it uses the proper features of electroencephalography. The results show that there are significant differences and abnormalities in the left hemisphere, (p < 0.05) at the electrodes AF3, F3, P7, T7, and O1 in the children with autism compared with the control group. Also, the evaluation of the obtained connections values between brain regions demonstrated that there are more abnormalities in the connectivity of frontal and parietal lobes and the relations of the neighboring regions in children with autism. It is observed that the proposed model is able to distinguish the autistic children from the control subjects with an accuracy rate of 95.1% based on the obtained values of CNN using the SVM method. [ABSTRACT FROM AUTHOR]

We have developed a cellular neural network formed by simplified processing elements composed of thin-film transistors. First, we simplified the neuron circuit into a two-inverter two-switch circuit and the synapse device into only a transistor. Next, we composed the processing elements of thin-film transistors, which are promising for giant microelectronics applications, and formed a cellular neural network by the processing elements. Finally, we confirmed that the cellular neural network can learn multiple logics even in a small-scale neural network. Moreover, we verified that the cellular neural network can simultaneously recognize multiple simple alphabet letters. These results should serve as the theoretical bases to realize ultra-large scale integration for brain-type integrated circuits. [ABSTRACT FROM AUTHOR]

This paper does present a comprehensive concept for a robust and reliable truck detection involving solely one single presence sensor (e.g. an inductive loop, but also any other presence sensor) at a signalized traffic junction. Hereby, two operations modes are distinguished: (a) during green traffic light phases, and (b) a much challenging case, during red traffic light phases. First, it is shown how difficult the underlying classification task is, this mainly due to strongly overlapped classes, which cannot be easily separated by simple hyper-planes. Then, a novel soft radial basis cellular neural/nonlinear network (SRB-CNN) based concept is developed, validated and extensively benchmarked with a selection of the best representatives of the current related state-of-the-art classification concepts (namely the following: support vector machines with radial basis function, artificial neural network, naive Bayes, and decision trees). For benchmarking purposes, all selected competing classifiers do use the same features and the superiority of the novel CNN based classifier is thereby underscored, as it strongly outperforms the other ones. This novel SRB-CNN based concept does satisfactorily fulfill the hard industrial requirements regarding robustness, low-cost, high processing speed, low memory consumption, and the capability to be deployed in low cost embedded systems. [ABSTRACT FROM AUTHOR]

This paper investigates a new type of stability, namely global generalized exponential stability of the nonautonomous delayed cellular neural networks. Several novel delay-dependent sufficient conditions are established by applying a new generalized Halanay inequality. In these conditions, the boundedness of time-varying delays and coefficients are not required. In addition, the effectiveness of these conditions is illustrated by two numerical examples. [ABSTRACT FROM AUTHOR]

This paper addresses the exponential stability of switched cellular neural networks by using the mode-dependent average dwell time (MDADT) approach. This method is quite different from the traditional average dwell time (ADT) method in permitting each subsystem to have its own average dwell time. Detailed investigations have been carried out for two cases. One is that all subsystems are stable and the other is that stable subsystems coexist with unstable subsystems. By employing Lyapunov functionals, linear matrix inequalities (LMIs), Jessen-type inequality, Wirtinger-based inequality, reciprocally convex approach, we derived some novel and less conservative conditions on exponential stability of the networks. Comparing to ADT, the proposed MDADT show that the minimal dwell time of each subsystem is smaller and the switched system stabilizes faster. The obtained results extend and improve some existing ones. Moreover, the validness and effectiveness of these results are demonstrated through numerical simulations. [ABSTRACT FROM AUTHOR]

The paper is concerned with the exponential convergence for a class of non-autonomous cellular neural networks with multi-proportional delays. By employing the differential inequality techniques, we establish a novel result to ensure that all solutions of the addressed system converge exponentially to zero vector. Our results complement with some recent ones. Moreover, an illustrative example and its numerical simulation are given to demonstrate the effectiveness of the obtained results. [ABSTRACT FROM AUTHOR]

Computer-aided Diagnosis (CADx) technology can substantially aid in early detection and diagnosis of breast cancers. However, the overall performance of a CADx system is tied, to a large extent, to the accuracy with which the tumors can be segmented in a mammogram. This implies that the segmentation of mammograms is a critical step in the diagnosis of benign and malignant tumors. In this paper, we develop an enhanced mammography CADx system with an emphasis on the segmentation step. In particular, we present two hybrid algorithms based upon region-based, contour-based and clustering segmentation techniques to recognize benign and malignant breast tumors. In the first algorithm, in order to obtain the most accurate final segmented tumor, the initial segmented image, that is required for the level set, is provided by one of spatial fuzzy clustering (SFC), improved region growing (RG), or cellular neural network (CNN). In the second algorithm, all of the parameters which control the level set are obtained from a dynamic training procedure by the combination of both genetic algorithms (GA) and artificial neural network (ANN) or memetic algorithm (MA) and ANN. After segmenting tumors using one of the hybrid proposed methods, intensity, shape and texture features are extracted from tumors, and the appropriate features are then selected by another GA algorithm. Finally, to classify tumors as benign or malignant, different classifiers such as ANN, random forest, naïve Bayes, support vector machine (SVM), and K-nearest neighbor (KNN) are used. Experimental results confirm the efficiency of the proposed methods in terms of sensitivity, specificity, accuracy and area under ROC curve (AUC) for the classification of breast tumors. It was concluded that RG and GA in adaptive RG-LS method produce more accurate primary boundary of tumors and appropriate parameters for the level set technique in segmentation and subsequently in classification. [ABSTRACT FROM AUTHOR]

Breast cancer is regarded as one of the most frequent mortality causes among women. As early detection of breast cancer increases the survival chance, creation of a system to diagnose suspicious masses in mammograms is important. In this paper, two automated methods are presented to diagnose mass types of benign and malignant in mammograms. In the first proposed method, segmentation is done using an automated region growing whose threshold is obtained by a trained artificial neural network (ANN). In the second proposed method, segmentation is performed by a cellular neural network (CNN) whose parameters are determined by a genetic algorithm (GA). Intensity, textural, and shape features are extracted from segmented tumors. GA is used to select appropriate features from the set of extracted features. In the next stage, ANNs are used to classify the mammograms as benign or malignant. To evaluate the performance of the proposed methods different classifiers (such as random forest, naïve Bayes, SVM, and KNN) are used. Results of the proposed techniques performed on MIAS and DDSM databases are promising. The obtained sensitivity, specificity, and accuracy rates are 96.87%, 95.94%, and 96.47%, respectively. [ABSTRACT FROM AUTHOR]

The cellular neural network (CNN) is one of the classic artificial neural networks. During the past decades, the one-dimensional CNN models and their applications have not yet been paid enough enthusiasm too. For this reason, this paper proposes a simplified one-dimensional CNN model and then designs a pairwise network using this model to demonstrate its applicability. This pairwise CNN consists of two parallel one-dimensional CNNs, a fixed master and a movable slave. Using this pairwise CNN, an algorithm is developed to perform the global alignment of two DNA sequences. In this algorithm, the slave moves forward step by step, and the cell states of the master are computed in the meanwhile. Based on all the states obtained in all time steps, a state selection array is generated then a global alignment path is determined from this array. Under the guidance of the alignment path, two DNA sequences are globally aligned by inserting blank spaces in the appropriate positions of these two sequences. Experiments on aligning the DNA sequences from the publicly available databases of the NCBI with this method are carried out in this paper and compared with the other two methods. Through evaluating computation time and similarity, these experiments prove that the proposed one-dimensional CNN model is effective, and the alignment algorithm based on a pairwise CNN of the model is efficient, obtaining higher similarity with less computation time than the other two. [ABSTRACT FROM AUTHOR]

Given a general Boolean function, an algorithm is proposed in this paper to find a sequence of robust uncoupled cellular neural networks, with logic operators as the conjunctions, implementing the given Boolean function. Each resulting robust uncoupled cellular neural network in the decomposition has a margin greater than or equal to a pre-specified value. For reasonable robustness levels, the proposed algorithm usually requires lesser number of searching templates and provides faster execution than those by using other similar methods. Furthermore, a mechanism for practical tradeoff between the guaranteed robustness and the complexity in terms of the number of terms in the decomposition is provided in our proposed algorithm. [ABSTRACT FROM AUTHOR]

Abstract: Image interpretation domains have witnessed the application of many intelligent methodologies over the past decade; however the effective use of evolutionary computing techniques for feature detection has been less explored. In this paper, we critically analyze the possibility of using cellular neural network for accurate feature detection. Contextual knowledge has been effectively represented by incorporating spectral and spatial aspects using adaptive kernel strategy. Developed methodology has been compared with traditional approaches in an object based context and investigations revealed that considerable success has been achieved with the procedure. Intelligent interpretation, automatic interpolation, and effective contextual representations are the features of the system. [Copyright &y& Elsevier]

Abstract: This paper proposes a new CNN architecture conceived for hardware implementation of complex ML-CNNs on programmable devices. The architecture is completely modular and expandable, and includes advanced features such as non-linear templates, time-variant coefficients or multi-layer structure. We also present an implementation platform based on the pre-designed but user-configurable FPGA processing modules that inherit the modularity and expandability of the logical architecture. All the modules share the same, properly designed, I/O interface, so the platform can be configured to accommodate CNNs of any size or structure, composed of a number of processing blocks that can be physically distributed over several FPGA boards. Our Carthagonova architecture makes use of a temporal processing approach with a super-pipelined unfolded cell structure, leading to the maximum degree of parallelism while still keeping the most efficient use of FPGA resources. Both the CNN architecture and the hardware platform have been validated by the implementation of a real-time video processing system, showing that they conform a valuable set of tools for the development of CNN-based applications. [Copyright &y& Elsevier]

Abstract: This paper concerns with cellular neural networks with time-varying delays in leakage (or forgetting) terms. Without assuming boundedness on activation functions, we establish sufficient conditions on existence and global exponential stability of almost periodic solutions by using Lyapunov functional method and differential inequality techniques. Our results complement with some recent ones. [Copyright &y& Elsevier]

Abstract: In this paper we study the stability of a stochastic neutral cellular neural network By using fixed point theory and some analysis techniques, we obtain new criteria for exponential stability in mean square of the considered stochastic neutral cellular neural network. Finally, an example is provided to illustrate the relevance of the results. [Copyright &y& Elsevier]

Abstract: In an earlier paper we utilized a novel method using cellular neural networks (CNNs) coupled with spherical harmonics method to solve the steady state neutron transport equation in x–y geometry. Here, the previous work is extended to the study of time-dependent neutron transport equation. To achieve this goal, an equivalent electrical circuit based on a second-order form of time-dependent neutron transport equation and one equivalent group of neutron precursor density is obtained by the CNN method. The CNN model is used to simulate step and ramp perturbation transients in a typical 2D core. [Copyright &y& Elsevier]

Abstract: All anomalies are important in the interpretation of gravity and magnetic data because they indicate some important structural features. One of the advantages of using gravity or magnetic data for searching contacts is to be detected buried structures whose signs could not be seen on the surface. In this paper, a general view of the cellular neural network (CNN) method with a large scale nonlinear circuit is presented focusing on its image processing applications. The proposed CNN model is used consecutively in order to extract body and body edges. The algorithm is a stochastic image processing method based on close neighborhood relationship of the cells and optimization of A, B and I matrices entitled as cloning template operators. Setting up a CNN (continues time cellular neural network (CTCNN) or discrete time cellular neural network (DTCNN)) for a particular task needs a proper selection of cloning templates which determine the dynamics of the method. The proposed algorithm is used for image enhancement and edge detection. The proposed method is applied on synthetic and field data generated for edge detection of near-surface geological bodies that mask each other in various depths and dimensions. The program named as CNNEDGEPOT is a set of functions written in MATLAB software. The GUI helps the user to easily change all the required CNN model parameters. A visual evaluation of the outputs due to DTCNN and CTCNN are carried out and the results are compared with each other. These examples demonstrate that in detecting the geological features the CNN model can be used for visual interpretation of near surface gravity or magnetic anomaly maps. [Copyright &y& Elsevier]

Abstract: Cellular neural networks proved to be a useful parallel computing system for image processing applications. Cellular neural networks (CNNs) constitute a class of recurrent and locally coupled arrays of identical cells. The connectivity among the cells is determined by a set of parameters called templates. CNN templates are the key parameters to perform a desired task. One of the challenging problems in designing templates is to find the optimal template that functions appropriately for the solution of the intended problem. In this paper, we have implemented the Iterative Annealing Optimization Method on the analog CNN chip to find an optimum template by training a randomly selected initial template. We have been able to show that the proposed system is efficient to find the suitable template for some specific image processing applications. [Copyright &y& Elsevier]

Abstract: This paper describes a novel method based on using cellular neural networks (CNN) coupled with spherical harmonics method (PN ) to solve the time-independent neutron transport equation in x–y geometry. To achieve this, an equivalent electrical circuit based on second-order form of neutron transport equation and relevant boundary conditions is obtained using CNN method. We use the CNN model to simulate spatial response of scalar flux distribution in the steady state condition for different order of spherical harmonics approximations. The accuracy, stability, and capabilities of CNN model are examined in 2D Cartesian geometry for fixed source and criticality problems. [Copyright &y& Elsevier]

Abstract: The complexity of hardware design methodologies represents a significant difficulty for non-hardware focused scientists working on accelerating the simulation of complex bio-inspired applications. An emerging generation of electronic system level (ESL) design tools is been developed, which allow software–hardware codesign and partitioning of complex algorithms from high level language (HLL) descriptions. These tools, together with high performance reconfigurable computer (HPRC) systems consisting of standard microprocessors coupled with application specific FPGA chips, provide a new approach for rapid emulation and acceleration of highly parallelizable algorithms. In this article CoDeveloper, and ESL IDE from Impulse Accelerated Technologies, are analyzed. A model for the first synapse of the retina, based on a discrete-time sequential CNN architecture suitable for FPGA implementation proposed by the authors in a previous paper, is implemented using CoDeveloper tools and the DS1002 HPRC platform from DRC Computers. Results showed that, with a minimum development time, a 10×acceleration, when compared to the software emulation, can be obtained. [Copyright &y& Elsevier]

Abstract: In a study (Szekely, 1965) of the locomotion of salamanders, it is observed that a ‘doubly periodic traveling wave solution’ of a logical neural network can be used to explain a dynamic pattern of movements. We show here that nonlinear and nonlogical artificial neural network can also be built by means of reaction diffusion principles and existence or nonexistence of doubly periodic traveling waves can be guaranteed by adjusting parameters built into these networks. Our derivations for existence are based on implicit function theorems and the invariance properties of our model; while nonexistence is based on boundedness properties of the polynomial reaction term. We also give illustrative examples as well as comments on the differences between present results with those obtained for linear models studied earlier in Cheng and Lin (2009) . [Copyright &y& Elsevier]

Abstract: It is well known that one-dimensional cellular neural networks (1D CNNs) with the template can perform connected component detection (CCD). However, this has been confirmed only by numerical and laboratory experiments. In this paper, sufficient conditions for 1D CNNs to perform CCD are obtained through theoretical analysis. Main result shows that a wide class of templates including can be used for CCD. [ABSTRACT FROM AUTHOR]

Abstract: In this paper, a cellular neural network whose state variables are governed by stochastic non-linear integro-differential equations is investigated. The considered delays are distributed continuously over unbounded intervals. By applying the Lyapunov functional method, the semimartingale convergence theorem, and some inequality technique, we obtain some sufficient criteria to check the almost sure exponential stability of the system, which generalizes and improves some earlier publications. Two examples are also given to demonstrate our results. [Copyright &y& Elsevier]

Abstract: This paper deals with compact travelling waves and peakon type solutions of several equations of mathematical physics and their Cellular Neural Network (CNN) realization. More precisely, we study different generalizations of the Camassa–Holm equation, of the Korteweg–de Vries equation and the nonlinear PDE describing the vibrations of a chain of particles interconnected by springs. In many cases the waves develop cusp type singularities at the peaks. In the second part of the paper the CNN realization of the compact travelling waves is fulfilled and the corresponding geometrical illustrations of the interaction of these waves are given. [Copyright &y& Elsevier]

Abstract: In this paper we propose a retinal architecture that incorporates the neural circuits found in the different retinal regions. It is implemented in a reconfigurable system for observing in real time the contrast processing capabilities of each retinal region over the provided stimuli. The retina model is based on a discrete-time cellular neural network (DTCNN) that will be implemented on reconfigurable architecture (FPGA) with a time multiplexing approach. This architecture is able to incorporate 50 million neurons in its structure for processing video in real time. It has been observed that the contrast detection and the detail resolution are influenced by the convergence factor of neurons and by the lateral inhibition, specific characteristics of each neural circuit. [Copyright &y& Elsevier]

Abstract: The computational paradigm represented by Cellular Neural/nonlinear Networks (CNN) and the CNN Universal Machine (CNN-UM) as a Cellular Wave Computer, gives new perspectives also for computational statistical physics. Thousands of locally interconnected cells working in parallel, analog signals giving the possibility of generating truly random numbers, continuity in time and the optical sensors included on the chip are just a few important advantages of such computers. Although CNN computers are mainly used and designed for image processing, here we argue that they are also suitable for solving complex problems in computational statistical physics. This study presents two examples of stochastic simulations on CNN: the site-percolation problem and the two-dimensional Ising model. Promising results are obtained using an ACE16K chip with 128×128 cells. In the second part of the work we discuss the possibility of using the CNN architecture in studying problems related to spin-glasses. A CNN with locally variant parameters is used for developing an optimization algorithm on spin-glass type models. Speed of the algorithms and further trends in developing the CNN chips are discussed. [Copyright &y& Elsevier]

Abstract: Although sigma–delta modulation is widely used for analog-to-digital (A/D) converters, sigma–delta concepts are only for 1D signals. Signal processing in the digital domain is extremely useful for 2D signals such as used in image processing, medical imaging, ultrasound imaging, and so on. The intricate task that provides true 2D sigma–delta modulation is feasible in the spatial domain sigma–delta modulation using the discrete-time cellular neural network (DT-CNN) with a C-template. In the proposed architecture, the A-template is used for a digital-to-analog converter (DAC), the C-template works as an integrator, and the nonlinear output function is used for the bilevel output. In addition, due to the cellular neural network (CNN) characteristics, each pixel of an image corresponds to a cell of a CNN, and each cell is connected spatially by the A-template. Therefore, the proposed system can be thought of as a very large-scale and super-parallel sigma–delta modulator. Moreover, the spatio-temporal dynamics is designed to obtain an optimal reconstruction signal. The experimental results show the excellent reconstruction performance and capabilities of the CNN as a sigma–delta modulator. [Copyright &y& Elsevier]

Abstract: This paper describes a novel architecture for the hardware implementation of non-linear multi-layer cellular neural networks (CNNs). This makes it feasible to design CNNs with millions of neurons accommodated in low price FPGA devices, being able to process standard video in real time. This architecture has been used to build a CNN-based model of the synapsis I of the fovea region, with the aim of implementing the basic spatial processing of the retina in reconfigurable hardware. The model is based on the receptive fields of the bipolar cells and mimics the retinal architecture achieving its processing capabilities. [Copyright &y& Elsevier]

Abstract: A novel fully automated system is introduced to facilitate lesion detection in dynamic contrast-enhanced, magnetic resonance mammography (DCE-MRM). The system extracts breast regions from pre-contrast images using a cellular neural network, generates normalized maximum intensity–time ratio (nMITR) maps and performs 3D template matching with three layers of cells to detect lesions. A breast is considered to be properly segmented when relative overlap and misclassification rate . Sensitivity, false-positive rate per slice and per lesion are used to assess detection performance. The system was tested with a dataset of 2064 breast MR images ( acquisitions over time) from 19 women containing 39 marked lesions. Ninety-seven percent of the breasts were segmented properly and all the lesions were detected correctly (detection ), however, there were some false-positive detections (31%/lesion, 10%/slice). [Copyright &y& Elsevier]

Abstract: A class of delayed cellular neural networks with impulses (DCNN) is investigated in this paper. Sufficient conditions are obtained for the existence of unique and globally exponential stable equilibriums of the DCNNs with Lipschitzian activation functions without assuming their boundedness, monotonicity or differentiability, but subjected to impulsive state displacement at fixed instants of time. The sufficient conditions are easy to verify and when the impulsive jumps are absent, the results reduce to those of the non-impulsive systems. Our investigations are based on employing Banach''s fixed point theorem, matrix and associated spectral theory. Our results generalize and significantly improve the previous known results due to this method. An example is given to show their feasibility and effectiveness. [Copyright &y& Elsevier]

Abstract: It is known that the complete stability of cellular neural networks with delays is very important in applications such as processing of a moving image. In this work, we utilize the Lyapunov functional method to analyse complete stability of cellular neural networks with delay. Our result is an improvement on that in [P.P. Civalleri, M. Gilli, L. Pandolfi, On stability of cellular neural networks with delay, IEEE Trans. Circuits Syst. I 40 (1993) 157–165]. [Copyright &y& Elsevier]

Abstract: In this Letter, we discuss discrete-time analogue of a continuous-time cellular neural network. Sufficient conditions are obtained for the existence of a unique almost periodic sequence solution which is globally attractive. Our results demonstrate dynamics of the formulated discrete-time analogue as mathematical models for the continuous-time cellular neural network in almost periodic case. Finally, a computer simulation illustrates the suitability of our discrete-time analogue as numerical algorithms in simulating the continuous-time cellular neural network conveniently. [Copyright &y& Elsevier]

Abstract: Employing Brouwer''s fixed point theorem, matrix theory, a continuation theorem of the coincidence degree and inequality analysis, the authors make a further investigation of a class of cellular neural networks with delays (DCNNs) in this Letter. A family of sufficient conditions are given for checking global exponential stability and the existence of periodic solutions of DCNNs. These results have important leading significance in the design and applications of globally stable DCNNs and periodic oscillatory DCNNs. Our results extend and improve some earlier publications. [Copyright &y& Elsevier]

Abstract: In this Letter, we have shown that the n-dimensional cellular neural network and delay cellular neural network can have not more than memory patterns, can have memory patterns which are locally exponentially stable. And we have obtained the estimates of attractive domain of such locally exponentially stable memory patterns. In addition, we have derived the conditions that the equilibrium point is locally exponentially stable when the equilibrium point locate the designated position. Some sufficient conditions have been obtained to guarantee the global exponential stability for the cellular neural networks. Those conditions can be directly derived from the parameters of the neural networks, are very easy to verified. The results presented in this Letter are the improvement and extension of the existed ones. Finally, the validity and performance of the results are illustrated by two simulation results. [Copyright &y& Elsevier]

Abstract: The Letter presents sufficient conditions ensuring the global exponential stability and existence of the periodic solution for cellular neural networks with variable delays. The results allow for the consideration of all unbounded neuron activation functions (but not necessarily surjective), in particular, can analyze the exponential stability and periodicity for the linear cellular neural networks. The work provides one such method which can be applied to cellular neural networks systems with variable delays. The method, based on the theory of fixed point and differential inequality technique. The applicability of the present results is demonstrated by two examples. [Copyright &y& Elsevier]

In this paper, a class of cellular neural networks with time-varying coefficients and delays is considered. By constructing a suitable Liapunov functional and utilizing the technique of matrix analysis, some new sufficient conditions on the global exponential stability of solutions are obtained. The results obtained in this paper improve and extend some of the previous results. [Copyright &y& Elsevier]

This paper is devoted to the existence and global attractivity of almost periodic solution for a class of cellular neural network with distributed delays and variable coefficients. Some sufficient conditions ensuring the existence and global attractivity of almost periodic solution are derived by employing Banach fixed point theory and using differential inequality technique. The results allow for the consideration of all unbounded neuron signal functions (but not necessarily surjective). Thus, these conditions obtained have highly important significance in designs and applications of the networks. We extend and improve previously known results. An example is also worked out to demonstrate the advantages of our results. [Copyright &y& Elsevier]

Summary: A new type of optoelectronic cellular neural network has been developed by providing the capability of coefficients adjusment of cellular neural network (CNN) using Widrow based perceptron learning algorithm. The new supervised cellular neural network is called Widrow-CNN. Despite the unsupervised CNN, the proposed learning algorithm allows to use the Widrow-CNN for various image processing applications easily. Also, the capability of CNN for image processing and feature extraction has been improved using basic joint transform correlation architecture. This hardware application presents high speed processing capability compared to digital applications. The optoelectronic Widrow-CNN has been tested for classic CNN feature extraction problems. It yields the best results even in case of hard feature extraction problems such as diagonal line detection and vertical line determination. [Copyright &y& Elsevier]