首页>
外国专利>
PARAMETER CONTROL METHOD AND GLOBAL OPTIMIZATION METHOD FOR NEURAL NETWORK
PARAMETER CONTROL METHOD AND GLOBAL OPTIMIZATION METHOD FOR NEURAL NETWORK
展开▼
机译:神经网络的参数控制方法和全局优化方法
展开▼
页面导航
摘要
著录项
相似文献
摘要
PURPOSE: To obtain an extremely satisfactory answer for an optimization problem at high speed by a definite method without using stochastic change in a neural network in which total input to each element and the state of each element are updated according to a specific equation by varying the value of a parameter within a specific range in a process to repeat such update. ;CONSTITUTION: In an intercoupling type neural network in which the output Xk of the element (k) is transmitted to the element (j) with weight Wjk, and WjkXk flows in the element (j), and also, on which input bias θj is added, and in which the total input Uj to each element and the state Xj(j=1,...n) of each element are updated according to equations I, II setting the parameter to control the influence of an output value before the state is updated as (r), and provided with a transfer function Sats like equation Ill assuming the parameter to control the inclination of the transfer function as (s), the values of the parameters (s) and (r) are varied within the range of equation IV in the process to repeat the state update of the element.;COPYRIGHT: (C)1994,JPO&Japio
展开▼
机译:目的:在不使用神经网络随机变化的情况下,通过确定的方法高速获得最满意的优化问题的答案,在该神经网络中,通过改变特定的方程式,可以根据特定的方程式更新每个元素的总输入量和每个元素的状态。在重复此更新的过程中特定范围内的参数值。 ;构成:在互耦型神经网络中,元素(k)的输出X k Sub>以权重W jk Sub>和W传输到元素(j) jk Sub> X k Sub>在元素(j)中流动,并且还添加了输入偏置θ j Sub>,并且在其中总输入根据等式I,II更新每个元素的U j Sub>和每个元素的状态X j Sub>(j = 1,... n),将参数设置为状态更新为(r)之前输出值的影响,并提供了传递函数Sats,如方程式Ill,假设控制传递函数的倾斜度的参数为(s),则参数的值(s) (r)在公式IV的范围内变化,以重复该元素的状态更新过程。;版权所有:(C)1994,JPO&Japio
展开▼