Dynamics of Transiently Chaotic Neural Network and Its Application to Optimization

Through adding a nonlinear self-feedback term in the evolution equations of nerual network,we introduced a transiently chaotic neural network model.In order to utilize the transiently chaotic dynamics mechanism in optimization problem efficiently,we have analyzed the dynamical pocedure of the transiently chaotic neural network model and studied the function of the crucial bifurcation parameter which governs the chaotic behavior of the system.Based on the dynamical analysis of the transiently chaotic neural network model,Chaotic annealing algorithm is also examined and improved.As an example,we applied chaotic annealing method to the traveling salesman problem and obtained good results.     

混沌神经网络的延时反馈控制研究

针对混沌神经网络，提出了一种改进的延时反馈控制方法. 利用该方法，当延时参数τ为奇数时，被控神经网络收敛于记忆模式以及它的反相模式的2周期上. 若选取不同的延时参数，被控网络则收敛于不同的周期态上. 关键词： 控制混沌 延时反馈控制 混沌神经网络     

Robust adaptive synchronization of chaotic neural networks by slide technique

In this paper, we focus on the robust adaptive synchronization between two coupled chaotic neural networks with all the parameters unknown and time-varying delay. In order to increase the robustness of the two coupled neural networks, the key idea is that a sliding-mode-type controller is employed. Moreover, without the estimate values of the network unknown parameters taken as an updating object, a new updating object is introduced in the constructing of controller. Using the proposed controller, without any requirements for the boundedness, monotonicity and differentiability of activation functions, and symmetry of connections, the two coupled chaotic neural networks can achieve global robust synchronization no matter what their initial states are. Finally, the numerical simulation validates the effectiveness and feasibility of the proposed technique.     

迟滞混沌神经元/网络的控制策略及应用研究

为了保持神经网络在优化计算求解过程中结构不被改变, 以迟滞混沌神经元和迟滞混沌神经网络为研究对象, 提出了一种基于滤波跟踪误差的控制策略来实现神经元/网络的稳定控制. 采用该控制策略, 在不改变非线性特性发生机理的情况下, 神经元/网络可实现函数优化计算问题的求解. 所设计的控制律包含两部分: 一部分是系统进入滤波跟踪误差面时的等效控制部分, 另一部分为确保系统快速进入滤波跟踪误差面的控制部分. 采用Lyapunov方法对神经元/网络的控制进行了稳定性证明. 根据待寻优函数直接求得神经元的控制律, 在该控制律的作用下, 神经元/网络可逐渐稳定到优化函数的极值点, 从而实现优化问题的求解, 仿真实验结果验证了该控制方法在优化计算中的可行性和有效性.     

Application of the edge of chaos in combinatorial optimization

Many problems in science, engineering and real life are related to the combinatorial optimization. However, many combinatorial optimization problems belong to a class of the NP-hard problems, and their globally optimal solutions are usually difficult to solve. Therefore, great attention has been attracted to the algorithms of searching the globally optimal solution or near-optimal solution for the combinatorial optimization problems. As a typical combinatorial optimization problem, the traveling salesman problem(TSP) often serves as a touchstone for novel approaches. It has been found that natural systems, particularly brain nervous systems, work at the critical region between order and disorder, namely,on the edge of chaos. In this work, an algorithm for the combinatorial optimization problems is proposed based on the neural networks on the edge of chaos(ECNN). The algorithm is then applied to TSPs of 10 cities, 21 cities, 48 cities and 70 cities. The results show that ECNN algorithm has strong ability to drive the networks away from local minimums.Compared with the transiently chaotic neural network(TCNN), the stochastic chaotic neural network(SCNN) algorithms and other optimization algorithms, much higher rates of globally optimal solutions and near-optimal solutions are obtained with ECNN algorithm. To conclude, our algorithm provides an effective way for solving the combinatorial optimization problems.     

Transversal homoclinic orbits in a transiently chaotic neural network

We study the existence of snap-back repellers, hence the existence of transversal homoclinic orbits in a discrete-time neural network. Chaotic behaviors for the network system in the sense of Li and Yorke or Marotto can then be concluded. The result is established by analyzing the structures of the system and allocating suitable parameters in constructing the fixed points and their pre-images for the system. The investigation provides a theoretical confirmation on the scenario of transient chaos for the system. All the parameter conditions for the theory can be examined numerically. The numerical ranges for the parameters which yield chaotic dynamics and convergent dynamics provide significant information in the annealing process in solving combinatorial optimization problems using this transiently chaotic neural network. (c) 2002 American Institute of Physics.     

Neural Network Structure Optimization by Simulated Annealing

A critical problem in large neural networks is over parameterization with a large number of weight parameters, which limits their use on edge devices due to prohibitive computational power and memory/storage requirements. To make neural networks more practical on edge devices and real-time industrial applications, they need to be compressed in advance. Since edge devices cannot train or access trained networks when internet resources are scarce, the preloading of smaller networks is essential. Various works in the literature have shown that the redundant branches can be pruned strategically in a fully connected network without sacrificing the performance significantly. However, majority of these methodologies need high computational resources to integrate weight training via the back-propagation algorithm during the process of network compression. In this work, we draw attention to the optimization of the network structure for preserving performance despite compression by pruning aggressively. The structure optimization is performed using the simulated annealing algorithm only, without utilizing back-propagation for branch weight training. Being a heuristic-based, non-convex optimization method, simulated annealing provides a globally near-optimal solution to this NP-hard problem for a given percentage of branch pruning. Our simulation results have shown that simulated annealing can significantly reduce the complexity of a fully connected network while maintaining the performance without the help of back-propagation.     

Nonlinear Time Series Prediction Using Chaotic Neural Networks

A nonlinear feedback term is introduced into the evaluation equation of weights of the backpropagation algorithm for neural network,the network becomes a chaotic one.For the purpose of that we can investigate how the different feedback terms affect the process of learning and forecasting,we use the model to forecast the nonlinear time series which is produced by Makey-Glass equation.By selecting the suitable feedback term,the system can escape from the local minima and converge to the global minimum or its approximate solutions,and the forecasting results are better than those of backpropagation algorithm.     

基于混沌神经网络的盲检测改进新算法

针对Hopfield神经网络的多起点问题,提出了一种新的基于混沌神经网络的盲信号检测算法,实现了二进制移相键控信号盲检测.据此进一步提出双sigmoid混沌神经网络模型,构造了新的能量函数,且证明了该模型的稳定性,并对网络参数进行配置.仿真实验表明:混沌神经网络能够避免局部极小点且具备较强的抗噪性能,双sigmoid混沌神经网络则继承了其所有的优点,且其收敛速度更快,仅需更短的接收数据即可到达全局真实平衡点,从而降低了算法的计算复杂度,减少了运行时间.     

基于遗传神经网络的旋转机械故障预测方法研究

许多大型旋转机械运行工况恶劣,非平稳、非线性特征明显,以及各种突发性、偶然性因素的影响,给基于振动信号处理的状态预测和状态维护分析带来困难。神经网络以其强大的处理非线性系统的能力在故障预测中得到广泛的应用,但由于其在追求高精度训练目标时易陷入局部极值,且收敛速度慢甚至发散。针对这个问题,提出了采用遗传算法对神经网络连接权值和阈值进行优化,这样不仅发挥了神经网络广泛的映射特性也使遗传算法的全局搜索优势尽显无疑。通过组合这两种算法,在提升网络学习的准确度方面,优点尤其突出,最终提高对旋转机械故障预测和寿命估计的性能,这在某环境模拟试验系统动力风机的轴承磨损故障预测中得到了验证。     

Neural networks and chaos: construction, evaluation of chaotic networks, and prediction of chaos with multilayer feedforward networks

Many research works deal with chaotic neural networks for various fields of application. Unfortunately, up to now, these networks are usually claimed to be chaotic without any mathematical proof. The purpose of this paper is to establish, based on a rigorous theoretical framework, an equivalence between chaotic iterations according to Devaney and a particular class of neural networks. On the one hand, we show how to build such a network, on the other hand, we provide a method to check if a neural network is a chaotic one. Finally, the ability of classical feedforward multilayer perceptrons to learn sets of data obtained from a dynamical system is regarded. Various boolean functions are iterated on finite states. Iterations of some of them are proven to be chaotic as it is defined by Devaney. In that context, important differences occur in the training process, establishing with various neural networks that chaotic behaviors are far more difficult to learn.     

Synchronization in complex delayed dynamical networks with impulsive effects

The present paper is mainly concerned with the issues of synchronization dynamics of complex delayed dynamical networks with impulsive effects. A general model of complex delayed dynamical networks with impulsive effects is formulated, which can well describe practical architectures of more realistic complex networks related to impulsive effects. Based on impulsive stability theory on delayed dynamical systems, some simple but less conservative criterion are derived for global synchronization of such dynamical network. It is shown that synchronization of the networks is heavily dependent on impulsive effects of connecting configuration in the networks. Furthermore, the theoretical results are applied to a typical SF network composing of impulsive coupled chaotic delayed Hopfield neural network nodes, and are also illustrated by numerical simulations.     

基于改进教学优化算法的Hermite正交基神经网络混沌时间序列预测

针对传统预测模型对混沌时间序列预测精度低、收敛速度慢及模型结构复杂的问题, 提出了基于改进教学优化算法的Hermite正交基神经网络预测模型. 首先, 将自相关法和Cao方法相结合对混沌时间序列进行相空间重构, 以获得重构延迟时间向量; 其次, 以Hermite正交基函数为激励函数构成Hermite正交基神经网络, 作为预测模型; 最后, 将模型参数优化问题转化为多维空间上的函数优化问题, 利用改进教学优化算法对预测模型进行参数优化, 以建立预测模型并进行预测分析. 分别以Lorenz 系统和Liu系统为模型, 通过四阶Runge-Kutta法产生混沌时间序列作为仿真对象, 并进行单步及多步预测对比实验. 仿真结果表明, 与径向基函数神经网络、回声状态网络、最小二乘支持向量机及基于教学优化算法的Hermite正交基神经网络预测模型相比, 所提预测模型具有更高的预测精度、更快的收敛速度和更简单的模型结构, 验证了该模型的高效性, 便于推广和应用.     

Cellular neural networks for welding arc thermograms segmentation

Machine vision systems are used in many areas for monitoring of technological processes. Among this processes welding takes important place, where often infrared cameras are used. Besides reliable hardware, successful application of vision systems requires suitable software based on proper algorithms. One of most important group of image processing algorithms is connected to image segmentation. Obtainment of exact boundary of an object that changes shape in time, such as the welding arc, represented on a thermogram is not a trivial task. In the paper a segmentation method using supervised approach based on a cellular neural networks is presented. Simulated annealing and genetic algorithm were used for training of the network (template optimization). Comparison of proposed method to a well elaborated segmentation method based on region growing approach was made. Obtained results prove that the cellular neural network can be a valuable tool for infrared welding pool images segmentation.     

Global synchronization in general complex delayed dynamical networks and its applications

The main objective of the present paper is further to investigate global synchronization of a general model of complex delayed dynamical networks. Based on stability theory on delayed dynamical systems, some simple yet less conservative criteria for both delay-independent and delay-dependent global synchronization of the networks are derived analytically. It is shown that under some conditions, if the uncoupled dynamical node is stable itself, then the network can be globally synchronized for any coupling delays as long as the coupling strength is small enough. On the other hand, if each dynamical node of the network is chaotic, then global synchronization of the networks is heavily dependent on the effects of coupling delays in addition to the connection configuration. Furthermore, the results are applied to some typical small-world (SW) and scale-free (SF) complex networks composing of coupled dynamical nodes such as the cellular neural networks (CNNs) and the chaotic FHN neuron oscillators, and numerical simulations are given to verify and also visualize the theoretical results.     

Adaptive synchronization of a class of fractional-order complex-valued chaotic neural network with time-delay

This paper is concerned with the adaptive synchronization of fractional-order complex-valued chaotic neural networks (FOCVCNNs) with time-delay. The chaotic behaviors of a class of fractional-order complex-valued neural network are investigated. Meanwhile, based on the complex-valued inequalities of fractional-order derivatives and the stability theory of fractional-order complex-valued systems, a new adaptive controller and new complex-valued update laws are proposed to construct a synchronization control model for fractional-order complex-valued chaotic neural networks. Finally, the numerical simulation results are presented to illustrate the effectiveness of the developed synchronization scheme.     

Chaotically Temporal Retrieval of Memory

A neural network with nonlinear delays to produce temporal retrieval of memory is presented. In this network, chaotic motion of the local fields provides a mechanism for the system to escape from one memory to another. It is proved by numerical investigations that the chaotic temporal process can explore the topological structure of the state space and the system has better efficiency of searching global minimum of the energy function than the Hopfield model. The characters of the system show that it may have great potential use in solving combinatorial optimization problems with its complex dynamics.     

神经系统中随机和混沌感知信号的联想记忆与分割

为了模拟人与动物感知信息的真实环境，以脉动神经元节点组成神经元网络，研究在随机刺激和混沌刺激等极端条件下的记忆模式存储与时间分割问题.研究表明：网络对于若干种模式的叠加输入，能够以一部分神经元同步发放的形式在时间域上分割出每一模式. 如果输入模式是缺损的，系统能够把它们恢复到原型，即具有联想记忆功能.通过调节耦合强度和噪声强度等参数使得网络在中等强度噪声达到最优的时间分割，与广泛讨论的随机共振现象一致. 关键词： 神经网络 空时模式 联想记忆 随机共振     

Synchronization of different chaotic systems via active radial basis functions sliding mode controller

This paper presents a new method to synchronize different chaotic systems with disturbances via an active radial basis function （RBF） sliding controller. This method incorporates the advantages of active control, neural network and sliding mode control. The main part of the controller is given based on the output of the RBF neural networks and the weights of these single layer networks are tuned on-line based on the sliding mode reaching law. Only several radial basis functions are required for this controller which takes the sliding mode variable as the only input. The proposed controller can make the synchronization error converge to zero quickly and can overcome external disturbances. Analysis of the stability for the controller is carried out based on the Lyapunov stability theorem. Finally, five examples are given to illustrate the robustness and effectiveness of the proposed synchronization control strategy.     

Support Vector Driven Genetic Algorithm for the Design of Circular Polarized Microstrip Antenna

In this paper, a hybrid soft computing method for designing specific microstrip antenna is presented. Evolutionary algorithm such as genetic algorithm (GA) is one of the promising ways of finding global optimum solution from a multivariate nonlinear feature space. Being a stochastic iterative algorithm, it requires much computation power when the function to be optimized is complex and time consuming. Various meta-modelling techniques such as neural network, response surface methods, kriging, etc. can be used to model the process under optimization in order to reduce the computational expenses. In this paper, we investigate one such technique – support vector regression (SVR) – to model the complex analytical process. The model, thus obtained, is used for optimization using genetic algorithms. This approach is demonstrated for the design of circular polarized microstrip antenna at 2.6 GHz band. The results of SVR model are compared with other meta-models generated with neural network and response surface methodology.