1) early restart algorithm
重置算法
1.
Then, in order to optimize the neural network structure, the early restart algorithm is introduced and applied to the NL2SOL feed (forward) neural network.
首先基于拟牛顿NL2SOL法构造前馈神经网络模型,为了优化神经网络结构,尝试引入重置算法(EarlyRestartAlgorithm),构建基于重置的NL2SOL动态前馈神经网络。
2.
Then, in order to optimize the neural network structure, the early restart algorithm is introduced and applied to the Quasi-Newton feed forward neural network.
构造基于拟牛顿法(Quasi-Newton Algorithm)的前馈神经网络模型,为了优化神经网络结构,尝试引入重置算法(Early Restart Algorithm),得到基于重置的拟牛顿动态前馈神经网络。
2) early-restart algorithm
重置算法
1.
This article applies the early-restart algorithm to the optimization of neural network s structure, studies the character of optimal restart time in the algorithm, and advances the revisable structure of classic BP neural network based on early-restart algorithm.
尝试将重置算法应用于经典BP神经网络的结构优化,研究了重置算法中最佳重置时间的性质,同时提出一种重置变结构经典BP神经网络。
2.
This paper combines the Back Propogation(BP) neural network with an early-restart algorithm and applies it to the hydrocarbon reservoir prediction,and the results verify that the neural network has better application prospective and realistic mea.
这里尝试着将与重置算法相结合的BP神经网络应用于油气储层预测方面,并证实重置神经网络具有更好的应用前景和现实意义。
3) cycled resetting algorithm(CR algorithm)
周期重置算法
4) post-algorithm
后置算法
1.
The post-algorithm and error compensation were discussed.
研究了离子束加工系统的后置算法和误差补偿等问题。
5) scrambling algorithm
置乱算法
1.
Periodicity and security of Arnold transformation are analyzed, and based on Arnold transformation a fast and secure image scrambling algorithm is proposed.
分析Arnold变换的周期性和安全性,在Arnold变换的基础上通过扩展,提出一种可对图像快速又安全置乱的置乱算法。
6) placement algorithms
配置算法
1.
Wavelength converter placement algorithms in all-optical tree networks;
树形全光网络中波长转换器配置算法
2.
Wavelength converter placement algorithms in wavelength-routed all-optical tree networks;
波长路由树形全光网中波长转换器配置算法
补充资料：不重置抽样
不重置抽样是从总体中每抽取一个样本单位后，不将其再放回总体内，因而任何单位一经抽出，就不会有再被抽取的可能性。这样，在抽样过程中，总体单位数是逐渐减少的，越抽到后来，留在总体中的单位越少，被抽中的可能性越大。
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