然后，在此框架下提出了基于遗传规划的单个神经元的设计方法，该方法可实现对神经元函数类型的优化。
Then, based on GP the design algorithm of single neuron, which realizes the auto-optimization of neuron function types, is proposed.
新算法选择很广一类的隐层神经元函数，可以直接求得全局最小点，不存在BP算法的局部极小、收敛速度慢等问题。
The algorithm can get global minimum easily with a wide variety of functions of hidden neurons, and no problems such as local minima and slow rate of convergence are suffered like BP algorithm.
通过采用非线性函数作为神经元的传递函数，使神经网络的非线性问题同力学的非线性问题得到统一。
The analytical scheme of nonlinear contact mechanics is corresponded to that of Neural Network by Considering nonlinear functions as nerve cell translation functions.
该网络把级数中的函数看成非线性神经元，建立油藏系统的函数型连接人工神经网络模型。
In the net, the functions are served as nonlinear neural units to establish function link artificial neural networks models of oil reservoir systems.
文章采用径向基函数神经元网络建立了加氢精制反应器数学模型。
Based on the radial basis function neural networks this paper has established a model of a catalytic hydrofining.
介绍了一种基于改进适应度函数的遗传单神经元控制方法。
A single neural node control based on genetic algorithm with improving fitness function is presented.
R BF神经网络的隐层神经元的作用可解释成从非线性可分空间向线性可分空间映射的函数。
The role of hidden layer neurons of a RBF neural network can be interpreted as a function which maps input patterns from a nonlinear separable space to a linear separable space.
提出一类基于基函数展开的双隐层过程神经元网络模型。
A class of process neural network model with two hidden-layer based on expansion of basis function is brought forward.
采用径向基函数神经元网络对实验数据进行训练，得到融合网络的权值。
The experimental data are trained using a radial base function artificial neural network, and the weight values for data fusion are obtained.
RBF神经网络是一种局部逼近的神经网络，理论上只要足够多的神经元，R BF神经网络可以任意精度逼近任意连续函数。
RBF neural network is a kind of local approximation neural networks. In theory, it can approximate any continuous function if there is enough neuron.
的关键，CNN是人工神经元，这是一个数学函数模仿生活神经元。
The key to the CNN is the artificial neuron, which is a mathematical function that imitates living neurons.
并且详细叙述了神经网络结构参数如隐含层神经元个数、激励函数、网络收敛精度等的确定原则和方法。
The principle and methods to determine the network parameters such as number of neuron in hidden layer, excitation function and the convergence accuracy have been analyzed in detail.
以往的BP算法调节神经元网络的权值，其网络的隐层结点数、网络学习快慢程度及网络的泛化能力都与网络的激励函数有关的。
BP algorithm is often used to correct weights of neural network because number of hidden nodes, studying speed and generation ability of neural network are related to activation function.
另一种是含有知识人工神经元的人工神经网络(NNKBN)，其知识人工神经元的活化函数是由扩展的经验公式构成。
The other is the neural network with knowledge-based neurons (NNKBN) where extended prior knowledge analytic formulas work as activation functions of the neurons.
然而，传统神经元的M - P模型用连接权值和非线性激活函数分别模仿神经元的突触和细胞体的作用。
However, the traditional M-P neuron model which used connective weights and a nonlinear activation function simulate the operation of neural's synapse and soma respectively.
采用径向基函数神经元网络对实验数据进行训练，得到融合网络的权值。
The experimental data are trained using a radial base function artificial neural network, and the weight values for data fusion are obtained. The results of data fusion are identical tot…
提出了一种结构简单的神经元分段线性输出函数SETMOS实现方式。
A simple implementation method of the piecewise linear output function of a neuron by SETMOS structure was proposed.
在输入空间中引入一组函数正交基，将输入函数和网络权函数表示为该组正交基的展开形式，利用基函数的正交性简化过程神经元聚合运算。
By introducing a group of function orthogonal basis into the input space, the input functions and the network weight functions are expressed in the expansion form.
该方法通过选择径向基函数中心、确定神经网络隐层神经元的数目和调整每一层的权值和阈值，对由于PSD非线性产生的误差进行修正。
The nonlinear error of PSD was modified by choosing the centre of RBF, ascertaining the number of neural cell of the neural network and adjusting the weight and the threshold of each hiberarchy.
该文通过编写S函数的方法建立增益自调整的神经元二自由度pid控制的SIMULINK仿真模型，并给出仿真结果。
In this paper, SIMULINK simulation model of gain self-regulative neuron two-degree-of-freedom PID control is established, which is based on S-function. Also the simulation results are presented.
该文通过编写S函数的方法建立增益自调整的神经元二自由度pid控制的SIMULINK仿真模型，并给出仿真结果。
In this paper, SIMULINK simulation model of gain self-regulative neuron two-degree-of-freedom PID control is established, which is based on S-function. Also the simulation results are presented.
应用推荐