This paper presents a novel neural network architecture based on fuzzy set theory, FIBP.
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。
The chosen neural network architecture consisted of one input layer, one hidden layer and the output layer.
我们选择的网络结构包括一个输入层、一个隐含层、一个输出层。
The characteristic parameter extraction, the neural network architecture and the network training are given.
文中介绍了特征参数的提取、神经网络的构成以及训练方法。
In this paper, a hybrid fuzzy neural network architecture is proposed for complex diagnosis objects. A series of fuzzy neural sub networks are integrated to perform the task of fault classification.
对于复杂的诊断对象，本文提出了一种复合模糊神经网络结构，该神经网络结构集成了一系列模糊神经子网络，来完成故障分类任务。
The architecture of neural network computing oriented parallel computer is the elementary aspect of artificial neural network research.
面向神经计算的并行计算机体系结构是神经网络研究中的一项重要工作。
The architecture of this neural network is relatively simple, and easily implemented by the hardware.
该神经网络模型结构简单，便于硬件实现。
The fusion architecture of the modified fuzzy counter propagation neural network is workable.
改进的模糊对向传播网络融合结构是可行的。
This paper provides a new architecture of neural network, called Loop architecture neural network (LANN), and its learning rules.
本文提出了一种称为环结构神经网络(LANN)模型及其学习算法。
A fuzzy counter propagation neural network (FCPN) based data fusion approach and a modified fuzzy counter propagation neural network (MFCPN) fusion architecture are proposed for target recognition.
针对数据融合和目标识别的特点，提出了基于模糊对向传播网络的融合目标识别方法和改进的模糊对向传播网络(MFCPN)融合结构。
Starting from the full life cycle of the building, the article used AHP and BP neural network method to build the low-carbon architecture evaluation system.
从建筑的全生命周期出发，本文利用层次分析法(ahp)和BP神经网络法构建低碳建筑评价体系。
CMAC (Cerebellar Model Articulation Controller) is a kind of local learning feed - forward neural network with simple architecture, quick learning convergence and effective implementation.
小脑模型清晰度控制器(CMAC)是一种局部学习前馈网络，结构简单，收敛速度快，易于实现。
Neural network possesses many of advantages : simple structure, easy implementation in hardware, the basic parallel computational architecture, etc.
人工神经网络的特点是：结构简单、能够大规模并行、容易用硬件实现等。
This paper proposes the classification of the neural network controller architecture and dynamic neural network structure, and clarifies its nonlinear mapping ability.
提出了神经网络控制器的分类以及非线性映射特性，讨论了神经网络控制器的特点。
Then, an observer bank of autoregressive time series models based on multi-component neural-network architecture is used for model diagnosis of rotor fault vibration signals.
最后根据该方法组成了一个自回归时间序列模型库，用于转子故障的模型诊断中。
The neural network with optimal architecture trained by evolutionary algorithm and Vogl algorithm is used to substitute the time-consuming finite element analysis.
该法使用具有较强非线性映射能力的神经网络模型代替有限元计算，提高了计算效率。
The neural network with optimal architecture trained by evolutionary algorithm and Vogl algorithm is used to substitute the time-consuming finite element analysis.
该法使用具有较强非线性映射能力的神经网络模型代替有限元计算，提高了计算效率。
应用推荐