首页 | 本学科首页   官方微博 | 高级检索  
相似文献
 共查询到20条相似文献,搜索用时 46 毫秒
1.
一种新型暂态混沌神经网络及其在函数优化中的应用   总被引:1,自引:0,他引:1  
本文提出了一种新颖的混沌神经元模型,其激励函数由Gauss函数和Sigmoid函数组成,分又图和Lyapunov指数的计算袁明其具有复杂的混沌动力学特性。在此基础上构成一种暂态混沌神经网络,将大范围的倍周期倒分叉过程的混沌搜索和最优解邻域内的类似Hopfield网络的梯度搜索相结合,应用于函数优化计算问题的求解。实验证明,它具有较
较强的全局寻优能力和较快的收敛速度。  相似文献   

2.
周婷  贾振红  刘秀玲 《计算机应用》2007,27(12):2910-2912
混沌神经网络能有效地解决函数优化问题。通过把sigmoid函数转化为墨西哥帽小波函数,而单一化退火因子函数被分段指数模拟退火函数所取代,提出了一种新型的混沌神经网络。与传统的混沌神经网络相比,该网络具有更强的全局寻优能力。仿真结果表明,小波混沌神经网络在搜索全局最优解的速度和精确度上都明显优于传统的混沌神经网络。  相似文献   

3.
混沌神经网络在求解优化问题中的应用   总被引:1,自引:0,他引:1  
本文运用GCM混沌神经网络对Hopfield神经网络在求解优化方面的问题进行了改进。通过混沌遍历,可使Hopfield网络在整个相空间进行搜索,从而避免网络在运行过程中陷入局部极小值。通过对一个对弈的实例进行实验,结果显示Hopfield网络的寻优特性获得了较大改进。  相似文献   

4.
混沌遗传算法及其在函数优化中的应用   总被引:11,自引:0,他引:11  
将混沌优化和遗传算法结合起来,提出了混沌遗传算法(CGA,Chaos Genetic Algorithm),并将其应用于函数优化问题的求解。通过在种群进化的不同阶段引入混沌优化操作,大大提升了遗传算法的整体性能。实验结果表明,与标准遗传算法(SGA)相比,该算法能更有效地求得全局最优解,具有更快的收敛速度。  相似文献   

5.
径向基函数神经网络的一种构造算法   总被引:4,自引:1,他引:4  
提出了径向基函数(RBF)神经网络参数的一种新的学习算法——分类优化迭代算法。在此基础上,设计了RBF网络的一种构造算法。仿真结果表明了本文方法的有效性。  相似文献   

6.
小波Hopfield神经网络及其在优化中的应用   总被引:3,自引:1,他引:3  
通过把Hopfield神经网络的sigmoid激励函数替换为Morlet小波函数,提出了一种新型的Hopfield神经网络——小波Hopfield神经网络(WHNN)。由于Morlet小波函数具有良好的局部逼近能力和较高的非线性度,因此WHNN在非线性函数寻优上表现出令人满意的较高精确度的效果。一个典型的函数优化例子表明小波Hopfield神经网络比Hopfield神经网络有较高的精确度。  相似文献   

7.
本文提出了用人工神经网络求解具有约束条件的非线性优化问题的具体方法,分析了神经网络能量函数的构成形式,并在常规的Hopfield网络模型的基础上构造了一个非全局连接的神经网络动力学模型。这种修改的Hopfield网络克服了常规的Hopfield网络在求解非线性优化问题时权值不好映射的困难,具有结构清晰,易于软件模拟和硬件实现的优点。  相似文献   

8.
如何设计高效、安全的带秘密密钥的单向函数一直是现代密码学研究中的一个热点。首先用神经网络来训练一维非线性分段映射产生混沌序列,并利用该模型产生的非线性序列构造带秘密密钥的Hash函数,该算法的优点之一是神经网络隐式混沌映射关系使直接获取映射关系变得困难,实验结果表明,这种算法具有对初值有高度敏感性、很好的单向性、弱碰撞性,较基于单一混沌映射的Hash函数具有更强的保密性能,且实现简单。  相似文献   

9.
一种混沌Hopfield网络及其在优化计算中的应用   总被引:2,自引:0,他引:2  
文章讨论了神经网络算法在约束优化问题中的应用,提出了一种混沌神经网络模型。在Hopfield网络中引入混沌机制,首先在混沌动态下搜索,然后利用HNN梯度优化搜索。对非线性函数的优化问题仿真表明算法具有很强的克服陷入局部极小能力。  相似文献   

10.
一种混沌Hopfiele网络及其在优化计算中的应用   总被引:2,自引:1,他引:2  
文章讨论了神经网络算法在约束优化问题中的应用,提出了一种混沌神经网络模型。在Hopfield网络中引入混沌机制,首先在混沌动态下搜索,然后利用HNN梯度优化搜索。对非线性函数的优化问题仿真表明算法具有很强的克服陷入局部极小能力。  相似文献   

11.
研究了一种具有随机邻居的2值元胞自动机模型的动力学性质,给出了其理想状态的动力学模型,分析了该模型的混沌特性,并通过分叉图、Lyapunov指数和Sehwarzian导数解释了模型由倍分叉通向混沌的过程。最后,通过计算对比,分析了非理想状态与理想状态下模型动力学性质的差异。  相似文献   

12.
Cellular particle swarm optimization   总被引:1,自引:0,他引:1  
This paper proposes a cellular particle swarm optimization (CPSO), hybridizing cellular automata (CA) and particle swarm optimization (PSO) for function optimization. In the proposed CPSO, a mechanism of CA is integrated in the velocity update to modify the trajectories of particles to avoid being trapped in the local optimum. With two different ways of integration of CA and PSO, two versions of CPSO, i.e. CPSO-inner and CPSO-outer, have been discussed. For the former, we devised three typical lattice structures of CA used as neighborhood, enabling particles to interact inside the swarm; and for the latter, a novel CA strategy based on “smart-cell” is designed, and particles employ the information from outside the swarm. Theoretical studies are made to analyze the convergence of CPSO, and numerical experiments are conducted to compare the proposed algorithm with different variants of PSO. According to the experimental results, the proposed method performs better than other variants of PSO on benchmark test functions.  相似文献   

13.
Recently, cellular neural networks (CNNs) have been demonstrated to be a highly effective paradigm applicable in a wide range of areas. Typically, CNNs can be implemented using VLSI circuits, but this would unavoidably require additional hardware. On the other hand, we can also implement CNNs purely by software; this, however, would result in very low performance when given a large CNN problem size. Nowadays, conventional desktop computers are usually equipped with programmable graphics processing units (GPUs) that can support parallel data processing. This paper introduces a GPU-based CNN simulator. In detail, we carefully organize the CNN data as 4-channel textures, and efficiently implement the CNN computation as fragment programs running in parallel on a GPU. In this way, we can create a high performance but low-cost CNN simulator. Experimentally, we demonstrate that the resultant GPU-based CNN simulator can run 8–17 times faster than a CPU-based CNN simulator.  相似文献   

14.
基于混沌变量,提出一种神经网络自适应控制系统的优化设计方案。采用混沌状态变量优化神经网络辨识器和控制器权参数,实现混沌粗搜索和局部细搜索相结合,搜索出控制系统参数的全局最优值,具有全局性、快速性、并行性。仿真实验表明采用该方案对强非线性对象的控制具有精度高、超调小、响应快、调节时间短等优点。  相似文献   

15.
Adaptive particle swarm optimization for CNN associative memories design   总被引:2,自引:0,他引:2  
Girolamo  Antonio   《Neurocomputing》2009,72(16-18):3851
In this paper particle swarm optimization is used to implement a synthesis procedure for cellular neural networks autoassociative memories. The use of this optimization technique allows a global search for computing the model parameters that identify designed memories, providing a synthesis procedure that takes into account the robustness of the solution. In particular, the design parameters can be modified during the convergence in order to guarantee minimum recall performances of the network in terms of robustness to noise overlapped to input patterns. Numerical results confirm the good performances of the designed networks when patterns are affected by different kinds of noise.  相似文献   

16.
This paper demonstrates that recurrent neural networks can be used effectively to estimate unknown, complicated nonlinear dynamics. The emphasis of this paper is on the distinguishable properties of dynamics at the edge of chaos, i.e., between ordered behavior and chaotic behavior. We introduce new stochastic parameters, defined as combinations of standard parameters, and reveal relations between these parameters and the complexity of the network dynamics by simulation experiments. We then propose a novel learning method whose core is to keep the complexity of the network dynamics to the dynamics phase which has been distinguished using formulations of the experimental relations. In this method, the standard parameters of neurons are changed by the core part and also according to the global error measure calculated by the well-known simple back-propagation algorithm. Some simulation studies show that the core part is effective for recurrent neural network learning, and suggest the existence of excellent learning ability at the edge of chaos. This work was presented, in part, at the Second International Symposium on Artificial Life and Robotics, Oita, Japan, February 18–20, 1997  相似文献   

17.
         下载免费PDF全文
Global exponential stability problems are investigated for cellularneural networks (CNN) with multiple time-varying delays. Several newcriteria in linear matrix inequality form or in algebraic form arepresented to ascertain the uniqueness and global exponentialstability of the equilibrium point for CNN with multipletime-varying delays and with constant time delays. The proposedmethod has the advantage of considering the difference of neuronalexcitatory and inhibitory effects, which is also computationallyefficient as it can be solved numerically using the recentlydeveloped interior-point algorithm or be checked using simplealgebraic calculation. In addition, the proposed results generalizeand improve upon some previous works. Two numerical examples areused to show the effectiveness of the obtained results.  相似文献   

18.
Global exponential stability problems are investigated for cellular neural networks (CNN) with multiple time-varying delays. Several new criteria in linear matrix inequality form or in algebraic form are presented to ascertain the uniqueness and global exponential stability of the equilibrium point for CNN with multiple time-varying delays and with constant time delays. The proposed method has the advantage of considering the difference of neuronal excitatory and inhibitory effects, which is also computationally efficient as it can be solved numerically using the recently developed interior-point algorithm or be checked using simple algebraic calculation. In addition, the proposed results generalize and improve upon some previous works. Two numerical examples are used to show the effectiveness of the obtained results.  相似文献   

19.
混沌系统辨识的一种新的生长型神经气方法   总被引:2,自引:0,他引:2       下载免费PDF全文
在自组织神经网络基础上,根据生物群落自然增长的机制,提出了一种新的生长型神经气的自组织算法,用于混沌系统的自组织辨识.该算法在学习样本的激励下能够动态地增加神经元,避免某些神经元可能出现的欠训练现象,从而极大地提高了网络整体训练的速度.最后以Lorenz系统为对象进行了仿真.  相似文献   

20.
改进的混沌优化方法及其应用   总被引:8,自引:0,他引:8  
提出一种改进的混沌优化方法,该方法利用混沌变量对当前点进行扰动,并且通过时变参数逐渐减小搜索进程中的扰动幅度,同时以一定方式确定了时变参数的初值。用改进后的方法对连续对象的全局优化问题进行优化,仿真结果表明,该方法可以显著提高收敛速度和精确性。  相似文献   

设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号