感知器培训规则是基于这样一种思路—权系数的调整是由目标和输出的差分方程表达式决定。
The perceptron training rule is based on the idea that weight modification is best determined by some fraction of the difference between target and output.
感知器以一种不同的而且可能更为直观的方式来使用权重。
A perceptron utilizes weights in a different and perhaps more intuitive way.
这里有一些与感知器算法相区别的重要不同点。
There are important differences from the perceptron algorithm.
例如,某些基本的神经网络,它们的感知器只倾向于学习线形函数(通过划一条线可以把函数输入解析到分类系统中)。
For instance, a certain kind of basic neural network, the perceptron, is biased to learning only linear functions (functions with inputs that can be separated into classifications by drawing a line).
一个使用这个规则的神经网络称为感知器,并且这个规则被称为感知器学习规则。
A neural net that USES this rule is known as a perceptron, and this rule is called the perceptron learning rule.
现在,如果true函数是布尔或,那么感知器将从三个训练实例中归纳出所有的实例。
Now, if the true function were Boolean or, then the perceptron would have correctly generalized from three training instances to the full set of instances.
感知器是一种有用的神经网络模型,可以对线性可分的模式进行正确分类。
Perceptron is a kind of useful neural network model and can classify the classification of the detachable linearity correctly.
深度学习模型的一个典型例子是前馈深度网络,或者说多层感知器(MLP)。
The quintessential example of a deep learning model is the feedforward deepnetwork or multilayer perceptron (MLP).
利用感知器异或函数获得了节点之间不断优化的连接关系,然后得到最优路径图。
The continually optimized connecting relation is gained via perceptron and XOR function, then the optimal path graph is found.
介绍一种用循环多层感知器神经网络实现符号逻辑推理系统的方法。
A method of implementing symbol logic inference system using recurrent multilayer perceptron neural networks is presented in this paper.
数值实验表明NNKBN模型在许多方面优于传统的多层感知器模型。
Numerical experiments show that the NNKBN model has many advantages over the conventional multi-layer perceptron model.
显然,感知器不是一个人类决策的完整模型!
Obviously, the perceptron isn't a complete model of human decision-making!
导出了便于VLSI实现的多项式感知器的格型实现算法,进行了计算机模拟,并给出了相应的数值结果。
A new lattice polynomial perceptron (LPP) model is derived, which is very suitable for VLSI implementation. Computer simulations have been carried out and the experimental results are given.
其中,对于多层感知器网络、径向基函数网络、多项式网络尤其关注。
Of great interest, popular multilayer perceptron (MLP), radial basis function (RBF) and polynomial neural networks are the focus of the paper.
研究适用于隐马尔可夫模型(HMM)结合多层感知器(mlp)的小词汇量混合语音识别系统的一种简化神经网络结构。
It is applicable to any small vocabulary hybrid speech recognition system that combines hidden Markov model (HMM) with multi-layer perceptron (MLP).
考虑到线性模型的一些缺点,本文随后应用神经网络理论,分别建立感知器预警模型和BP网络预警模型。
Because liner models have some defects, I construct perceptron model and BP model on base of neural networks theory.
本文采用多层感知器建立了微带不连续性的神经网络模型。
The multi-layer perceptron is introduced to charcacterize the microstrip discontinuity by describings-parameters.
本文提出一种模糊核超球感知器(FKHP)学习方法,并介绍了一种基于FKHP这种学习方法的模糊分类模型。
This paper introduces a fuzzy classification model based on the proposed fuzzy kernel hyperball perceptron(FKHP) learning method.
一般对特定的基于多层感知器的故障诊断问题,很难确定神经网络的结构。
Generally, it is difficult to determine in advance a suitable network structure when a multi layer perceptron neural networks is used for a special fault diagnosis problem.
针对单隐层感知器的硬件设计进行了计算机仿真,得到了满足设计要求的隐层神经元个数和量化比特数。
For multilayer perceptron with single hidden layer, the computer simulation is done to get the number of hidden neurons and quantization bit which satisfy the design requirement.
在结合数据融合和数据挖掘的医疗监护模型的建模方面,采用多层感知器网络和决策树方法建立报警决策器的模型。
For modeling of medical ward based on data fusion and data mining, multi - layer perceptron network and decision trees are used.
提出了用粗糙集理论构造模糊多层感知器的方法。
A method of constructing knowledge based fuzzy perceptron based on rough sets theory is proposed.
风速的反演是基于多层感知器网络;
The network for retrieving wind speed is a multi-layer perceptron.
本文提出了平均误比特率最小意义下的最佳线性多用户信号检测器,并给出了求解这种最佳线性多用户信号检测器的近似方法——训练单层感知器法。
This paper presented a optimum linear multiuser detector in terms of minimum mean bit error rate, and given a approximate method of solving the detector - method of training single perceptron.
提出了训练前多层感知器硬件设计的灵敏度分析方法。
The sensitivity analysis approach for the hardware implementation of multilayer perceptron prior to network training is proposed.
针对一类基于模糊感知器的神经模糊分类器,分析了隶属函数限制条件对分类结果的影响。
For a neuro_fuzzy classifier based on the fuzzy perceptron, this paper analyses how membership function constraints affect the classification result.
分离系统由多层感知器(非线性部分)后接一个线性盲解卷过程(线性部分)组成。
The separating system consists of a multilayer perceptron (nonlinear part) followed by a linear blind deconvolution (linear part).
本文研究了非高斯噪声中信号的检测,采用多层感知器神经网络作为检测器。
In this paper, the authors study the detection of signals in non-Gaussian noise, and employ a multilayer perceptron neural network as a detector.
本文研究了非高斯噪声中信号的检测,采用多层感知器神经网络作为检测器。
In this paper, the authors study the detection of signals in non-Gaussian noise, and employ a multilayer perceptron neural network as a detector.
应用推荐