Empirical results show that genetic programming model is more advantageous than traditional statistical models, neural network models and decision tree models in prediction accuracy and robustness.
检验结果表明，该模型在预测精度、实用价值和鲁棒性方面都优于传统的统计模型、神经网络模型和决策树模型。
Genetic Algorithms is used in solving the mathematical model, it can obtain the global optimum even if there exists local optimums, and enlarge the application range of Fuzzy Physical Programming.
利用遗传算法求解数学模型，解决了最终优化目标可能存在多个局部最优解的问题，拓宽了模糊物理规划的应用范围。
The paper proposes a novel method for the identification of Hammerstein model based on genetic programming.
该文基于遗传规划提出了一种辨识哈默·斯坦模型的新方法。
On the basis of training data, the optimum model was obtained by genetic programming, and the accuracy of it was verified with the verifying data.
依据训练样本数据，经过遗传规划法求得最优预测模型，并用检验样本数据对所得的预测模型进行检验。
The method based on genetic programming to automatic model the function need not to estimate empirical formulas, only need the sample data and accuracy.
采用基于遗传程序设计方法实现函数自动建模无需预先确立经验模型，只需指定样本数据和精度要求即可获得回归表达式。
A new bilevel programming model-bilevel stochastic programming model is presented and the genetic algorithms based on Monte Carlo simulation to solve bilevel stochastic programming problem is given.
信用资产组合模型的分布计算是信用计量模型中一个非常重要的主题，对于这个问题一般常用的方法是进行蒙特卡罗随机模拟。
A new bilevel programming model-bilevel stochastic programming model is presented and the genetic algorithms based on Monte Carlo simulation to solve bilevel stochastic programming problem is given.
信用资产组合模型的分布计算是信用计量模型中一个非常重要的主题，对于这个问题一般常用的方法是进行蒙特卡罗随机模拟。
应用推荐