提出了一类新的模糊神经网络结构。
神经网络结构及权值优化属两级进化方法。
Simultaneity optimization for structure and weight distribution of neural network belongs to two class evolutionary method.
修剪法是确定和优化神经网络结构的重要方法之一。
Pruning algorithm is an important method to set up and optimize the structure of neural network model.
非毗邻层连接的前馈神经网络结构有极快的收敛速度。
The front feedback nerve network structure of not-adjacent layer conjunction has splitting velocity on convergence.
提出一种关于多层前向神经网络结构的混沌优化设计方法。
The optimization design method is proposed for feed-forward neural network structure by means of chaos ergodicity and randomicity.
提出了一个基于模糊集理论的新的神经网络结构及其学习算法。
This paper presents a novel neural network architecture based on fuzzy set theory, FIBP.
提出一种新的基于自谐振神经网络结构的自适应故障选相元件。
This paper presents a new adaptive phase selector with an adaptive resonance theory (ART) based neural network.
在此基础上提出了基于模态参数的BP神经网络结构损伤识别方法。
Based on this, bring forward the BP neural network structural damage detection method based on modal parameters.
用神经网络识别手写体数字，大多数采用的是单个的神经网络结构。
Most of the neural network handwritten digits recognition systems adopt a net - work with single structure.
为此本文首次提出一种新的神经网络结构：分布式多子网神经网络。
For this problem, a new neural network construction named distributed multi-subnet neural network is presented for the first time in this paper.
具有容错能力的人工神经网络结构，可以提高人工神经网络的可靠性。
The artificial neural network model with capacity of error-tolerance can improve the reliability considerably.
文章提出了一种新的优化神经网络结构及权值的方法——两级进化的方法。
This paper proposes a new optimizing neural network structure and weight distribution method two-step evolutionary method.
本文提出了改进的RBF神经网络结构、核函数个数、位置与宽度优化算法。
This paper presents an adaptive algorithm of optimally determining the structures, number, positions and widths of kernel functions of the improved radial basis function (IRBF) neural networks.
本文提出一种改进的神经网络结构，它由线性网络和多层前向网络两部分组成。
A modified neural network structure which is composed of a linear network and a multilayered feedforward neural network (MFNN) is presented.
设计了预测回采巷道锚杆支护参数的神经网络结构，并根据BP算法编制了软件。
A bolt supporting parameter selection neural network construction has been developed, the software is programmed based on BP algorithm.
然后文章提出用遗传算法来优化神经网络结构，从而从整体上提升疾病诊断模型的性能。
Acordingly, it proposed that optimize the structure of neural network using genetic algorithms, so as to enhance the overall performance of disease diagnostic model.
针对神经网络的结构存在冗余的问题，提出了一种利用粗糙集优化神经网络结构的方法。
In allusion to the redundancy of neural network structure, a optimizing method of neural network structure based on rough sets is established.
通过对神经网络集成的理论分析，提出了一种多级神经网络结构的手写体汉字识别模型。
By analyzing the theory of neural network integration, I developed a multi-level neural network model for recognition handwritten Chinese characters.
同时可以辅助的进行故障诊断，可由已建好的神经网络结构进行正向计算，推理出最后结果。
In the fault diagnosis, proceeds positive-going calculation by using the created neural network structure to infer the final result.
主要介绍了模拟电路故障诊断的新方法及测试原理，重点讲解了神经网络结构中参数选择方案。
It mainly introduces new methods of diagnosing simulation circuit trouble and testing principles, explains the scheme of choosing neural network structure parameter especially.
考虑工业系统故障预知的滞后，软件设计中采用了特殊的复合神经网络结构以便于维护和拓展。
Considered the lag of the fault detection, the design introduces a specific compound network architecture that makes the software convenient for maintainability and extension.
文中结合神经网络工作原理，构建了判定模块间重启相关度及模块可达集的神经网络结构模型。
This paper researches the principium of artificial neural network, puts forward the model of artificial neural network which determines the degree of restart dependence bet.
实验数据被用来训练径向基函数(RBF)神经网络，得出的神经网络结构和参数用于数据融合。
The experimental data are used to train a radial basis function (RBF) artificial neural network, and the construction and parameters of the network are obtained for data fusion.
其次，论文引入了神经网络，设计了用于无功电流检测的BP神经网络结构，并给出了相应算法。
Secondly, in this thesis, a structure of BP Neural Network for detecting reactive current is designed and the corresponding algorithm is given.
介绍了利用RBF神经网络进行数据非线性校正的原理以及RBF神经网络结构和参数的确定方法。
In this paper, the principle of nonlinear correction of data by using RBF neural network, the structure of neural network and the determination method of parameters are described.
本文研究了模糊神经网络，用神经网络结构进行模糊推理，用BP算法调节和优化具有局部性的参数。
In this paper, fuzzy neural network was studied and fuzzy reasoning was realized by use of neural networks structure. BP algorithm is used to optimize local parameter.
研究神经网络模型的结构和算法的分离与结合理论及结合神经网络结构描述语言实现底层代码的重用。
The separation of structure and algorithm in NN simulating model and how to reuse the code of NN through language description are introduced.
研究神经网络模型的结构和算法的分离与结合理论及结合神经网络结构描述语言实现底层代码的重用。
The separation of structure and algorithm in NN simulating model and how to reuse the code of NN through language description are introduced.
应用推荐