分析了遗传系数学习时所遇到的问题，提出了鲁棒学习的概念和方法；
Primary problems in learning inherited parameters are analyzed and concept and methods of robust learning are presented.
结果表明：1。不同环境下遗传距离的相关系数与所用的研究性状关系密切。
The results indicates1. The correlation coefficients of genetic distance under different environmental conditions closely relate to the selected characters.
进而通过计算遗传相似系数进行聚类分析。
The genetic similar coefficient was calculated and cluster analysis was conducted.
沙打旺野生材料间遗传分化明显，其基因分化系数比育成品种间和地方材料间大。
Genetic differentiation among wild materials was obvious and gene differentiation coefficient of it was larger than of bred varieties and local materials.
产量的遗传变异系数最大，为17.59%；
The genetic variation coefficient of yield was highest (17.59%).
把遗传算法和差异信息熵理论结合给出了优化分辨系数的方法。
Optimization method of the distinguishing coefficient is set up, on the basis of the integration of genetic algorithm(GA)and the difference information entropy in grey theory.
数据经遗传统计学处理，估算出体成分及无氧功率的对内相关系数和遗传度。
Inner correlation coefficient and heritability of body composition and anaerobic power were estimated by heredity statistics.
相似性分析结果显示：不同菌株之间遗传相似性系数相差较大。
Similarity analysis showed that genetic similarity coefficient between different strains has large difference.
数量遗传分析表明，各生长指标的遗传变异系数、表型变异系数和广义遗传力一般均大于生理指标；
Quantity genetic analysis showed that genetic variation coefficient, performative variation coefficient and hereditary ability of growth properties were greater than physiological properties.
从RAPD带型聚类图分析，普通桃类的遗传相似系数较高，基因交换频繁。
Putong peach had higher genetic similarity and frequency of gene exchange by dendrogram of RAPD bands.
数值算例表明，遗传神经网络在求解坝基岩体渗透系数反演问题中具有较高的计算效率和识别精度。
The presented numerical example shows that the genetic neural network is of both higher computing efficiency and higher identification accuracy.
遗传通径分析结果表明，穗粒数与水溶性戊聚糖含量之间的直接通径系数与其遗传相关系数基本一致。
The path analysis showed that the coefficient of direct path and genetic correlation was equivalent between grains number per spike and water soluble pentosan content.
来自我国西南以及日本两地区的小豆种质遗传离散度较大，遗传分化系数、相似系数平均值较低。
The material from Southwest China and Japan has relatively high genetic dispersion, low Gst and average value of genetic similarity coefficient.
结果表明：性状间的遗传相关系数绝大多数大于表型相关系数，且方向基本一致。
The results showed that most character heredity correlation coefficients was bigger than the phenotype correlation coefficients, also the direction was basically consistent.
首先，对数字中频接收机理论基础进行叙述。并讲述了用于优化数字滤波器系数的遗传算法原理和算法。
First, the theory and basic knowledge of digital Intermediate Frequency receiver and the Genetic Algorithms principle for optimizing the quantization coefficient of the digital filter are expatiated.
根据ISSR遗传相似系数划分的类群主要同染色体数目有关，也与地理分布有一定关系。
The species divided according to ISSR genetic similarity factors are mainly associated with chromosome number and to some extent with their geographic distribution.
提出了一种利用遗传算法优化前向神经网络的结构和正则项系数的混合学习算法。
A hybrid learning approach is presented in which genetic algorithms are used to optimize both the network architecture and the regularization coefficient.
计算各样本间的相似性系数和遗传距离，并采用UPGMA法对遗传距离进行了聚类分析。
Genetic similarities were calculated using simple matching coefficient, and the phenogram was constructed by using UPGMA method. Three cultivars of n.
表型变异系数均大于遗传变异系数。
Phenotypic variation coefficients were all greater than the genetic variation coefficients.
菌系间的遗传相似系数变化在0.45 ~ 0.93之间，多数菌系间的同源程度较低。
Genetic similarity coefficients within the isolates were among 0.45 ~ 0.93, there existed a low degree of homogeneity between most of them.
按广义遗传力法选用研究性状则相关系数大。
Bigger correlation coefficients can be obtained by the broad heritability method.
此外，通过遗传算法对模糊神经网络的学习速率和惯性系数等进行了优化，为控制系统实现最优控制提供了有力保证。
In addition, the paper makes use of Genetic Algorithms to optimize learning rates and inertia coefficients of Fuzzy-neural network, which can ensure that the controller achieves optimization control.
以考查点、难度系数和题型为主要控制参数建立了组卷问题的数学模型，并给出了用遗传算法解决组卷问题的新方法。
This paper presented a mathematical model with the main controlling parameters of the main points of knowledge, coefficient of difficulty and the structure of test question.
采用遗传算法来优化单脉冲阵列天线的和、差方向图和方向性系数。
The sum and difference patterns as well as the directivity of the monopulse antenna arrays are optimized based on genetic algorithms (GA).
两个群体间的相似性系数高达0.9187，彼此间的遗传距离仅为0.0848，体现出两个人工选育群体的遗传分化程度较低。
Nei's genetic identity and genetic distance between the two populations were 0.9187 and 0.0848, respectively, which indicated low genetic differentiation between the two populations.
新收集材料与其它资源间的平均遗传相似系数为0.1918。
The average similarity coefficient of newly-collected materials with other ones was 0.1918.
新收集材料与其它资源间的平均遗传相似系数为0.1918。
The average similarity coefficient of newly-collected materials with other ones was 0.1918.
应用推荐