1) Rule learning algorithm
规则学习算法
2) ant colony rule set learning
蚁群规则学习算法
3) learning rule
学习规则
1.
Discovering New Neural Network Learning Rule Based on Genetic Programming;
基于GP的神经网络学习规则的发现
2.
The weights of the principal component neural networks are trained with the aid of the algorithm of generalized Hebbian learning rule, and the input vectors of the local spatial features and image pixels value are transformed into feature vectors which are once clustered by Kmeans classifier, the road surface and unroad surface can be distinguish.
该方法用广义Hebb学习规则训练主元神经网络权值,然后将局部统计特征和图像像素值输入主元神经网络得到图像特征矢量,最后用K 均值分类器对该矢量进行分类,通过参考区域识别道路。
3.
In this neural network training, the author applied an error back-propagation gradient descending search technique successfully, and then proposed a new learning rule for multiple pattern pairs fuzzy associative memories in single FAM and its efficiency has been confirmed by computer imitations.
本文给出了模糊联想记忆神经网络联想输出误差函数的一种梯度计算方法,成功地把误差逆传播梯度下降搜索技术应用于该网络的训练中,提出一种新的多模式对模糊联想记忆的学习规则,计算机模拟表明该规则是十分有效的。
4) rules learning
规则学习
1.
The rules are made up by the method of rules learning,which can strengthen the portability of the system.
采用学习的方式来进行规则的生成,这种规则学习的方式使系统的可移植性大大增强。
5) rule learning
规则学习
1.
Based on the in-deep research on inductive learning theory, a rule learning algorithm is applied in building the intrusion detection model.
在对归纳学习理论深入研究的基础上,将规则学习算法应用到入侵检测建模中。
6) learning rules
学习规则
1.
Research new IF model and learning rules;
新IF模型及其学习规则研究
2.
The paper introduces the development history and features of the artificial neural network(ANN), summarizes the basic theory and learning rules of ANN, and cornments on the actualities,existing problems and tendency of its applications in oil & coal supervision of power plant chemistry.
介绍人工神经网络的发展及特点,对神经网络基础理论及各种学习规则和模型进行了概述,并且评述了目前人工神经网络在电厂化学油煤监督应用的现状、存在的问题及发展趋势。
3.
In this paper, the learning rules of MFNNs are proposed and their convergence properties are studied.
在此基础上 ,提出了单体模糊神经网络 (MFNNs)的学习规则并进一步研究了其收敛性 。
补充资料:逆推学习算法
分子式:
CAS号:
性质:又称逆推学习算法,简称BP算法,是1986年鲁梅哈特(D. E. Rumelhart)和麦克莱朗德(J. L. McClelland)提出来的。用样本数据训练人工神经网络(一种模仿人脑的信息处理系统),它自动地将实际输出值和期望值进行比较,得到误差信号,再根据误差信号从后(输出层)向前(输入层)逐层反传,调节各神经层神经元之间的连接权重,直至误差减至满足要求为止。反向传播算法的主要特征是中间层能对输出层反传过来的误差进行学习。这种算法不能保证训练期间实现全局误差最小,但可以实现局部误差最小。BP算法在图像处理、语音处理、优化等领域得到应用。
CAS号:
性质:又称逆推学习算法,简称BP算法,是1986年鲁梅哈特(D. E. Rumelhart)和麦克莱朗德(J. L. McClelland)提出来的。用样本数据训练人工神经网络(一种模仿人脑的信息处理系统),它自动地将实际输出值和期望值进行比较,得到误差信号,再根据误差信号从后(输出层)向前(输入层)逐层反传,调节各神经层神经元之间的连接权重,直至误差减至满足要求为止。反向传播算法的主要特征是中间层能对输出层反传过来的误差进行学习。这种算法不能保证训练期间实现全局误差最小,但可以实现局部误差最小。BP算法在图像处理、语音处理、优化等领域得到应用。
说明:补充资料仅用于学习参考,请勿用于其它任何用途。
参考词条