Design Of Cellular Neural Networks Research Articles

Novel High-Efficiency Nanocomposite Gate Design of Quantum-Dot Cellular Automata Based on Deep Learning.

With the development of science and technology, the feature size of CMOS devices will always shrink to the limit. Therefore, some new nanodevices will eventually become substitutes for microelectronic devices. A new electronic revolution will break out. Nanoscience and technology is the high-tech frontier technology of the century and one of the main contents of scientific development in the new era. Its development will have a profound impact on other disciplines, industries, and society. Nanoelectronics is an important part of the discipline of nanoscience and technology, which represents the development trend of microelectronics and will become the foundation of the next generation of electronic science and technology. With the development of ultra-large-scale integrated circuits, the feature size of electronic devices is getting smaller and smaller and has entered the nanoscale from the microscale. When the size of the system is small enough to be compared with the wavelength of electrons, the quantum effect becomes the dominant current-carrying main factor in child behavior. While these new phenomena and new effects bring challenges to the original semiconductor devices, they also provide opportunities for the development of new devices. Evolutionary circuit design is based on cellular neural network and quantum-dot cells, designs combinational logic circuits through the evolutionary algorithm, uses the logic gate based on cellular neural network design as the population gene of evolutionary circuit design, enriches the diversity of the population, and improves the evolutionary algorithm at the same time, the success rate of the improved genetic algorithm for evolutionary circuits has been greatly improved, and the failure rate has been reduced from 14% to 2%, obtaining a faster evolution speed and improving the performance of the evolution circuit.

A Memristive Multilayer Cellular Neural Network With Applications to Image Processing

The memristor has been extensively studied in electrical engineering and biological sciences as a means to compactly implement the synaptic function in neural networks. The cellular neural network (CNN) is one of the most implementable artificial neural network models and capable of massively parallel analog processing. In this paper, a novel memristive multilayer CNN (Mm-CNN) model is presented along with its performance analysis and applications. In this new CNN design, the memristor crossbar circuit acts as the synapse, which realizes one signed synaptic weight with a pair of memristors and performs the synaptic weighting compactly and linearly. Moreover, the complex weighted summation is executed in an efficient way with a proper design of Mm-CNN cell circuits. The proposed Mm-CNN has several merits, such as compactness, nonvolatility, versatility, and programmability of synaptic weights. Its performance in several image processing applications is illustrated through simulations.

Design of Cellular Neural Network (CNN) Simulator Based on Matlab for Brain Tumor Detection

Design of Cellular Neural Network (CNN) Simulator Based on Matlab for Brain Tumor Detection

Spatially distributed cellular neural networks

PurposeThe purpose of this paper is to develop a methodology for the design of cellular neural networks with interconnection topologies optimized and suitable for spatially distributed implementation.Design/methodology/approachThe authors perform combinatorial optimization on the neural network's topology to obtain a sparser network, in which the links between the components of the network that reside in different physical locations are minimized. The approach builds on existing computationally efficient tools for the design of cellular neural networks and uses the concept of the network's stability parameters to assess the performance of the network prior to testing.FindingsIt turns out that the sparser cellular neural networks thus produced exhibit performance that can be on par with that of networks with full connectivity, and that for implementations of modest size, communication delays are not that significant to affect the stability of the dynamical system.Originality/valueThe novelty of the proposed approach lies in the formulation of the combinatorial optimization problem in a way that trades‐off network performance for communication overhead, and the use of this method for the physical implementation of associative memories across different interconnected processors.

New Digital Architecture of CNN for Pattern Recognition

New Digital Architecture of CNN for Pattern RecognitionThe paper deals with the design of a new digital CNN (Cellular Neural Network) architecture for pattern recognition. The main parameters of the new design were the area consumption of the chip and the speed of calculation in one iteration. The CNN was designed as a digital synchronous circuit. The largest area of the chip belongs to the multiplication unit. In the new architecture we replaced the parallel multiplication unit by a simple AND gate performing serial multiplication. The natural property of this method of multiplication is rounding. We verified some basic properties of the proposed CNN such as edge detection, filling of the edges and noise removing. At the end we compared the designed network with other two CNNs. The new architecture allows to save till 86% gates in comparison with CNN with parallel multipliers.

Cellular Neural Networks With Virtual Template Expansion for Retinal Vessel Segmentation

A retinal vessel segmentation method based on cellular neural networks (CNNs) is proposed. The CNN design is characterized by a virtual template expansion obtained through a multistep operation. It is based on linear space-invariant 3times3 templates and can be realized using existing chip prototypes like the ACE16K. The proposed design is capable of performing vessel segmentation within a short computation time. It was tested on a publicly available database of color images of the retina, using receiver operating characteristic curves. The simulation results show good performance comparable with that of the best existing methods

An improvement of the design method of cellular neural networks based on generalized eigenvalue minimization

Realization of associative memories by cellular neural networks (CNNs) with binary output is studied. Concerning this problem, a CNN design method based upon generalized eigenvalue minimization (GEVM) has recently been proposed. In this brief, a new CNN design method which is based on the GEVM-based method will be presented. We first give some analytical results related to the basin of attraction of a memory vector. We then derive the design method by combining these analytical results and the GEVM-based method. We finally show through computer simulations that the proposed method can achieve higher recall probability than the original GEVM-based method.

NOVEL STABILITY CONDITIONS FOR CELLULAR NEURAL NETWORKS WITH TIME DELAY

In this paper, the global asymptotic stability of cellular neural networks with time delay is discussed using some novel Lyapunov functionals. Novel sufficient conditions for this type of stability are derived. They are less restrictive and more practical than those currently used. As a result, the design of cellular neural networks with time delay is refined. Our work can also be generalized to cellular neural networks with time-varying delay, a topic on which little research work has been done. By means of several different Lyapunov functionals, some sufficient conditions related to the global asymptotic stability for cellular neural networks with perturbations of time-varying delays are derived.

An optimization approach to design of cellular neural networks

In this paper, we consider the problem of realizing associative memories via cellular neural networks (CNNs). After introducing qualitative properties of the CNN model, we formulate the synthesis of CNNs that can store given binary vectors with improved performance as a constrained optimization problem. Next, we observe that this problem's constraints can be transformed into simple inequalities involving linear matrix inequalities. Finally, we reformulate the synthesis problem as a generalized eigenvalue problem, which can be efficiently solved by recently developed interior point methods. The validity of the proposed approach is illustrated by a design example.

A one-dimensional CMOS focal plane array for Gabor-type image filtering

We describe the design, implementation, and test results from an analog complementary metal-oxide-semiconductor very large scale integration (CMOS VLSI) chip which combines photosensing and an image filtering operation similar to Gabor filtering. The chip contains a one-dimensional (1-D) 27-pixel array and generates three outputs at every pixel; the input image intensity and the real and imaginary parts of the filter output. These results validate experimentally a recently presented theoretical framework for the design of cellular neural network (CNN) templates for Gabor-type spatial image filtering.

Gabor-type filtering in space and time with cellular neural networks

Gabor filters are preprocessing stages in image-processing and computer-vision applications. One drawback is that they are computationally intensive on a digital computer. This paper describes the design of cellular neural networks (CNNs) which compute the outputs of filters similar to Gabor filters. Analog VLSI implementations of these CNNs might eventually relieve the computational bottleneck associated with Gabor filtering image-processing algorithms. The CNNs compute both the real and imaginary parts of the filter outputs simultaneously, which is an important feature in applying them in algorithms utilizing the phase of the Gabor output.

Cloning template design of cellular neural networks for associative memories

This brief presents a synthesis procedure (design algorithm) for cellular neural networks with space-invariant cloning template with applications to associative memories. The design algorithm makes it possible to determine in a systematic manner cloning templates for cellular neural networks with or without symmetry constraints on the interconnection weights. Two specific examples are included to demonstrate the applicability of the methodology developed herein.

On the OP-amp based circuit design of cellular neural networks

On the OP-amp based circuit design of cellular neural networks

Sparsely interconnected neural networks for associative memories with applications to cellular neural networks

We first present results for the analysis and synthesis of a class of neural networks without any restrictions on the interconnecting structure. The class of neural networks which we consider have the structure of analog Hopfield nets and utilize saturation functions to model the neurons. Our analysis results make it possible to locate in a systematic manner all equilibrium points of the neural network and to determine the stability properties of the equilibrium points. The synthesis procedure makes it possible to design in a systematic manner neural networks (for associative memories) which store all desired memory patterns as reachable memory vectors. We generalize the above results to develop a design procedure for neural networks with sparse coefficient matrices. Our results guarantee that the synthesized neural networks have predetermined sparse interconnection structures and store any set of desired memory patterns as reachable memory vectors. We show that a sufficient condition for the existence of a sparse neural network design is self feedback for every neuron in the network. We apply our synthesis procedure to the design of cellular neural networks for associative memories. Our design procedure for neural networks with sparse interconnecting structure can take into account various problems encountered in VLSI realizations of such networks. For example, our procedure can be used to design neural networks with few or without any line-crossings resulting from the network interconnections. Several specific examples are included to demonstrate the applicability of the methodology advanced herein. >

The improvement of the hardware design of artificial CNN and a fast algorithm of CNN component detector

Cellular neural network (CNN) is a type of analog, nonlinear, real-time parallel processing network. The paper studies an implementation of the integrated operational amplifier used in the design of an artificial CNN. It improves the implementation of CNN proposed by Chua. A 4 x 4 artificial CNN circuit is designed, obtaining a better characteristic of a CNN connected component detector. Finally, a fast algorithm for a CNN component detector is given which proves to be very simple and quite convenient.

Design of robust cellular neural networks

Shows how to systematically design an inputless cellular neural network (CNN), which processes only the information present in the initial state, with prescribed stable and unstable outputs while simultaneously maximizing its robustness with respect to changes of its parameters. This is achieved by combining a generalization of previous results on CNN design with a design centering algorithm based on linear programming. The design process is highly efficient with small numbers of cells, and it can be precisely and flexible controlled. Many kinds of implementation-related constraints may be introduced, including bounded parameters and arbitrary topological restrictions. A nonrigorous but effective practical guideline for shaping the basins of attraction of stable outputs is recommended. A simple example is given and thoroughly discussed. >

Cellular neural network design for solving specific image‐processing problems

AbstractThis paper is concerned with determining simple CNN‐paradigm‐based circuits for solving specific binary image‐processing problems. Single‐layer CNN templates for performing specified shape extraction, extraction of shapes which contain a desired feature and modified feature detection are derived using a formulated design strategy. the concept of CNNs composed of modified cells is developed and circuits designed for realizing simultaneous detection of distinct features and for extracting horizontal line midpoints are presented.