mlps

Fuzzy Linear Analysis of MLPs and Its Applications

多层感知器的模糊线性分析及应用

The principle of MLPS and influence factors were discussed in the last , main influence factors were pointed out .

最后讨论了微液相法的原理和影响反应的因素，指出了影响该方法的主要因素和改进方向。

He specifically pointed to Master Limited Partnerships , or MLPs .

他特别指出了业主有限合伙制企业。

An optimal algorithm for IR / visual image registration based on Main-Line-Pairs ( MLPs ) is presented .

提出了一种基于干线对的红外与可见光图像配准算法。

The experimental results show that the proposed modular MLPs as well as the dynamic learning algorithm have not only fast learning speed but also good generalization performance .

结果表明，本文提出的神经网络动态学习算法不仅具有学习速度快，而且具有良好的推广性能。

Taking a MLP with a single hidden layer for an example , a semi-linear analysis theory of internal behavior of MLPs is presented .

作者以单隐层的MLP为例，论述了关于MLP的内部行为的半线性分析理论。

The number of the hidden layers of multilayer perceptrons ( MLPs ) is analyzed , and three-layer perceptrons neural network is adopted ;

对多层感知器隐层数进行了分析，确定采用三层感知器神经网络；

This paper describes a clear interpretation of internal behaviors of multi-layer perceptrons ( MLPs ) used for pattern classifications , functional approximations , and parameter estimations .

本文对用于模式分类、函数逼近、参数估计的多层感知器（MLPs）给出1个清晰的关于内部行为的解释。

A model combining MLP with fuzzy-set approach , the MLPs with N-2-1 or N-H-1 architecture , and the method of initializing weights are proposed .

建立了MLP和模糊集相结合的新模型；分析了MLP的结构为N-2-1和N-H-1，给出权重初始化的方法；

Extending this theory , this paper analyzes the sigmoidal neurons and the internal behaviors of single hidden-layer perceptrons ( MLPs ) with sigmoid neurons trained for pattern classifications .

本文将此理论扩展到非线性sigmoid神经元，分析了用来解决模式分类问题的、由sigmoid神经元构成的单隐层MLP（多层感知机）的内部行为；

You saw strong investor demand in high-growth sectors like life science and technology . You also had a lot of issuance of yield product in a surprisingly low rate environment & primarily MLPs but also Reits .

你会看到投资者对生命科学和高科技等高增长板块的强劲需求，也会看到，即便在利率很低的环境中，也出现了许多新发行的高收益产品&主要是MLP企业，还有REIT企业。

Based on this approach , by using the property of the two-dimensional structure possessed by the HMM , a simplified neural network architecture consisting of multiple simple MLPs , employed to estimate observation probabilities is achieved .

基于这种利用HMM的二维结构特性的方法，实现了用一种由多个简单的MLP所组成的简化神经网络结构来估计状态观测概率。

Experimental results show that this EP trained MLP model can generate a chaotic series , whose attractor can be reconstructed better than that generated by the BP trained MLP model and which generates many chaotic sequences by changing weights of this MLPs very easily .

计算机仿真结果表明：该模型比BP算法训练的神经网络模型能更好地重构混沌吸引子，调整网络权值即可产生多种混沌序列。