共查询到19条相似文献,搜索用时 484 毫秒
1.
2.
3.
4.
5.
章用一种免疫进化规划来设计多层前馈神经网络.该免疫进化规划在保留传统进化规划的随机全局搜索能力的能力的基础上,引进生物免疫中抗体通过浓度相互作用的机制和多样性保持机制.免疫进化规划的全局收敛性更优,并且具有很强的自适应环境的能力.实验结果验证了免疫进化规划在设计神经网络时的高效能. 相似文献
6.
7.
提出了一种基于梯度投影矩阵下的求解线性约束下规划问题的神经网络。针对解的稳定性问题,导出了该网络相关参数之间的关系。由文中定义可知,该网络不但适合于求解线性约束下线性或非二次规划问题,而且也用于求解线性或非线性方程组问题,比其它规划问题的神经网络方法更具有一般性。 相似文献
8.
全局优化的神经网络方法 总被引:3,自引:0,他引:3
提出了一种解全局优化问题的神经网络模型, 并分析了该模型的收敛性与可行性. 然后, 给出了一个算法, 严格地证明了该算法对优化问题的任意给定的初始点, 都能收敛到它的一个全局极小点. 最后的仿真结果表明, 该算法是有效的. 相似文献
9.
在求解一维连续型动态规划问题的自创算法一离散近似迭代法的基础上,结合双收敛方法,对多维连续型动态规划问题进行计算.该算法的基本思路为:在给定其他状态向量序列的基础上,每次对一个状态变量序列进行离散近似迭代,并找出该状态变量的最优序列,直到所有状态向量序列都检查完,当模型为非凸非凹动态规划时,证明了该算法的收敛性;当模型为凸动态规划时,证明了该算法的线性收敛性,最后,通过具体算例验证了该模型和算法的有效性. 相似文献
10.
11.
Youshen Xia Jun Wang 《Neural Networks, IEEE Transactions on》2000,11(4):1017-1022
Global exponential stability is a desirable property for dynamic systems. The paper studies the global exponential stability of several existing recurrent neural networks for solving linear programming problems, convex programming problems with interval constraints, convex programming problems with nonlinear constraints, and monotone variational inequalities. In contrast to the existing results on global exponential stability, the present results do not require additional conditions on the weight matrices of recurrent neural networks and improve some existing conditions for global exponential stability. Therefore, the stability results in the paper further demonstrate the superior convergence properties of the existing neural networks for optimization. 相似文献
12.
Projection type neural network for optimization problems has advantages over other networks for fewer parameters , low searching space dimension and simple structure. In this paper, by properly constructing a Lyapunov energy function, we have proven the global convergence of this network when being used to optimize a continuously differentiable convex function defined on a closed convex set. The result settles the extensive applicability of the network. Several numerical examples are given to verify the efficiency of the network. 相似文献
13.
This paper presents an algorithm for globally maximizing a sum of convex–convex ratios problem with a convex feasible region, which does not require involving all the functions to be differentiable and requires that their sub-gradients can be calculated efficiently. To our knowledge, little progress has been made for globally solving this problem so far. The algorithm uses a branch and bound scheme in which the main computational effort involves solving a sequence of linear programming subproblems. Because of these properties, the algorithm offers a potentially attractive means for globally solving the sum of convex–convex ratios problem over a convex feasible region. It has been proved that the algorithm possesses global convergence. Finally, the numerical experiments are given to show the feasibility of the proposed algorithm. 相似文献
14.
同时使用动量和自适应步长技巧的自适应矩估计(Adaptive Moment Estimation,Adam)型算法广泛应用于深度学习中.针对此方法不能同时在理论和实验上达到最优这一问题,文中结合AdaBelief灵活调整步长提高实验性能的技巧,以及仅采用指数移动平均(Exponential Moving Average,EMA)策略调整步长的Heavy-Ball动量方法加速收敛的优点,提出基于AdaBelief的Heavy-Ball动量方法.借鉴AdaBelief和Heavy-Ball动量方法收敛性分析的技巧,巧妙选取时变步长、动量系数,并利用添加动量项和自适应矩阵的方法,证明文中方法对于非光滑一般凸优化问题具有最优的个体收敛速率.最后,在凸优化问题和深度神经网络上的实验验证理论分析的正确性,并且证实文中方法可在理论上达到最优收敛性的同时提高性能. 相似文献
15.
Projection type neural network and its convergence analysis 总被引:1,自引:0,他引:1
Projection type neural network for optimization problems has advantages over other networks for fewer parameters , low searching space dimension and simple structure. In this paper, by properly constructing a Lyapunov energy function, we have proven the global convergence of this network when being used to optimize a continuously differentiable convex function defined on a closed convex set. The result settles the extensive applicability of the network. Several numerical examples are given to verify the efficiency of the network. 相似文献
16.
1 Introduction Optimization problems arise in a broad variety of scientific and engineering applica- tions. For many practice engineering applications problems, the real-time solutions of optimization problems are mostly required. One possible and very pr… 相似文献
17.
针对黑猩猩优化算法存在易陷入局部最优、收敛速度慢、寻优精度低等缺陷,提出混合改进策略的黑猩猩优化算法(SLWChOA).首先,利用Sobol序列初始化种群,增加种群的随机性和多样性,为算法全局寻优奠定基础;其次,引入基于凸透镜成像的反向学习策略,将其应用到当前最优个体上产生新的个体,提高算法的收敛精度和速度;同时,将水波动态自适应因子添加到攻击者位置更新处,增强算法跳出局部最优的能力;最后,通过10个基准测试函数、Wilcoxon秩和检验以及部分CEC2014函数进行仿真实验来评价改进算法的寻优性能,实验结果表明,所提算法在寻优精度、收敛速度和鲁棒性上均较对比算法有较大提升.另外,通过一个机械优化设计实验进行测试分析,进一步验证了SLWChOA的可行性和适用性. 相似文献
18.
19.
Alvaro R. De Pierro Elias Salomão Helou Neto 《International Transactions in Operational Research》2009,16(4):495-504
We describe the evolution of projection methods for solving convex feasibility problems to optimization methods when inconsistency arises, finally deriving from them, in a natural way, a general block method for convex constrained optimization. We present convergence results. 相似文献