网络函数

In this paper,continuous differentiable conditios of output response functions of Hopfied neural networks in usual papers is reduced to Lipschitz condition.

因此，本文将通常论文中Hopfield神经网络的输出响应函数连续可微的假设削弱为满足L ipschitz条件。

Simultaneously, as the self-organization mapping neural network does not has the competitive learning characteristic of an objective function, the method is free from the problem of local extremum.

同时，由于自组织映射神经网络的无目标函数的竞争学习特性，本方法摆脱了局部极值问题。

Relationships between the equilibrium points of neural networks and the local minimum points of energy functions are discussed.

1引言美国物理学家Hopfield教授在80年代提出用能量函数的方法判别神经网络的稳定性［1～3］。

Based on logarithmic function, a new backoff algorithm was presented by introducing the parameter which could change with the network state, in allusion to the deficiencies of Binary Exponential Backoff algorithm of IEEE 802.11 MAC.

针对IEEE 802.11 MAC协议二进制退避算法存在的缺陷，引入随网络状态变化的参数，提出了一种基于对数函数的新退避算法。

The real-time learning ability and the fast convergence of the recurrent network model of nonlinear dynamical system have been obtained by introducing the forgetting factor in the objective function and the maximum likelihood estimation principle.

本算法在目标函数中引入了遗忘因子，并借助于非线性系统的最大似然估计原理成功地解决了动态非线性系统回归神经网络模型权系数学习的实时性和快速性问题。

Considering the real speech mixture model could be nonlinear-convolution mixture model, the author presents a new nonlinear speech separation algorithm by utilizing the Finite Impulse Response neural network and the GMM pdf estimation, based on the feedback architecture and the Maximum Likelihood principle.

考虑到真实多通道语音分离系统的输入混合语音有可能是不同语音源信号的非线性混合而不是简单的线性混合，基于反馈结构，采用GMM概率密度函数估计方法，作者提出了一种采用有限冲激响应神经网络的非线性、卷积混合盲信号处理语音分离批处理新算法。

In the algorithm, radial-basis function neural network was utilized as forward model, and genetic algorithm was used to solve the optimization problem in the inverse problem, which can avoid the local minimum solution possibly encountered in the iterative inverse algorithm based on gradient descent and consequently achieve the global optimized solution of the inverse problem.

在该算法中，径向基函数神经网络用作前向模型，遗传算法用于求解逆问题中的优化问题，其优点是能够避免基于梯度下降法的迭代逆算法中可能遇到的局部最小问题，并能得到逆问题的全局最优解。

Based on the analysis of immune theory and Hopfield neural network, a new algorithm for multimodal function optimization was proposed.

分析了免疫算法和Hopfild神经网络的优缺点，提出了一种解决多峰值函数优化问题的混合算法。

Based on the functional link network, a new algorithm is proposed to solve the multi-objective optimization problems in engineering structures.

基于函数联接神经网络，提出了一种解决工程结构多目标模糊优化问题的新算法。

In this paper, the super-network method is used to analyze the operation process of the supply chains and construct a super-network of the supply chains. In order to decompose total demand with given distribution function, customer choice theory is adopted to acquire the demand of each supply chain. By combining game theory with Newsvendor model, we put forward a revenue-share contract, which can coordinate the behaviors of the members included in a same supply chain under the environment of SC vs. SC competition.

本文利用超网络方法分析供应链运作过程，建立了两条竞争供应链的超网络结构；已知产品总需求的随机分布函数，运用顾客选择理论得到每条供应链的产品需求情况；利用博弈理论和Newsvendor模型，得到了供应链竞争环境下可协调链内成员的收益共享合同。

Neither the killing of Mr Zarqawi nor any breakthrough on the political front will stop the insurgency and the fratricidal murders in their tracks.

在对危险的南部地区访问时，他斥责什叶派民兵领导人对中央集权的挑衅行为。

In fact,I've got him on the satellite mobile right now.

实际上 我们已接通卫星可视电话了