所设计的进化神经网络经实际应用取得了很好的结果，表明该方法是有效的。
This encoding method is used in the proposed evolutionary ANN. The results show that it is effective.
提出一种新的模块化进化神经网络方法，用于大规模或复杂问题的神经网络设计。
Inspired from modular programming, we proposed a module based evolutionary programming of ANNs, which puts emphasis on inheriting from the learned networks of small scale problem.
所以在此基础上，利用进化神经网络，采取BP算法和遗传算法建立了真核生物基因启动子识别模型。
On the basis of evolutionary neural network, the recognition model of promoter in eukaryote's gene was built using BP algorithms and genetic algorithms.
为了对微波谐振腔含水率测量结果进行校正，提出一种基于IA - BP优化算法的进化神经网络模型。
In order to correct the measuring results of moisture from microwave resonator, the IA-BP optimization algorithm based evolutionary neural network model is presented.
考虑到冲击地压时序的特点，采用基于免疫进化规划的进化神经网络进行了冲击地压非线性系统的建模研究。
Considering the dynamic character of rock burst, a time serial model of rock burst is constructed by evolutionary neural network based on immunized evolutionary program.
并以具体的边坡工程为实例，给出了基于IGIAS的三维可视化辅助分析，以及边坡危险性分区进化神经网络方法。
Finally, based on the IGIAS, a case study related to three-dimensional visualization and hazard subzone by using evolutionary artificial neural network is presented.
利用此进化神经网络较准确地表达了滑坡加固方案中设计参数与加固后滑坡的总体稳定性和工程造价之间的复杂映射关系。
Using this improved evolutionary neural network, the complex relationship between the design parameters and the stability after reinforcement and the cost of the project is expressed successfully.
本文在考虑多个参数对雨衰减非线性影响的基础上，建立了基于进化神经网络的雨衰减模型，并与ITU - R模型进行了比较。
Considering the nonlinear affects of various parameters on rain attenuation, we propose a new rain attenuation model based on evolutionary neural network and compare it with the ITU-R model.
讨论了进化神经网络的起源，从辅助式进化神经网络和结合式进化神经网络评述了进化神经网络的研究现状，阐述了进化神经网络的并行实现。
The paper discusses the origin of ENN, remarks the present researching situation of ENN from the auxiliary ENN and the combined ENN, then expatiates on the parallel implement of ENN.
并采用一个矿山实测得到的震级数列进行了进化神经网络方法的实用性验证，结果表明，进化神经网络不但模型拟合精度高，而且预测性能也较好。
The proposed model is tested by a real magnitude series from a mine, and results show that evolutionary neural network model has not only high precision, but also high prediction.
近几年来，进化神经网络研究已成为神经网络领域的一个新的研究热点，初步研究已经取得了许多有价值的结论和成果，为工程上的广泛深入应用带来了充满希望的前景。
In the recent years, evolutionary neural networks have been a new hot research. Initial research work have achieved many valuable results and bring prospect for deep application in engineer.
有意思的是，神经网络是一种对学习型评估的进化，算法经过训练后其行为就像是一个人类专家。
It is interesting to note that Neural Networks is an evolution of learning-oriented estimation, in which the method algorithm is trained to behave like a human expert.
这是一个被称为“神经网”的松散的神经网络，华盛顿特区的乔治华盛顿大学研究大脑进化的切特·舍伍德说。
It's a loose network of nerves called a "nerve net," says Chet Sherwood, who studies brain evolution at The George Washington University in Washington, d.c..
他发现进化后的大脑在执行其设定的任务时比传统的神经网络大脑具有更好的表现。
He has found that his evolved brains have become better than traditional neural network brains at the tasks he sets.
说实话，在计算机科学的一些主要分支学科的命名上就可以看出生物学的影子，譬如人工神经网络，遗传算法和进化计算法等等。
Indeed, the names of major subfields of computer science-such as artificial neural networks, genetic algorithms, and evolutionary computation-attest to the influence of biological analogies.
用神经网络构造机器人周围环境及障碍物的描述模型，用免疫进化算法寻找最佳路径。
Constructs the description model of environment and obstacle with neural network. Asks for the best path with immune evolution algorithm.
文章提出了一种新的优化神经网络结构及权值的方法——两级进化的方法。
This paper proposes a new optimizing neural network structure and weight distribution method two-step evolutionary method.
人工免疫学是继神经网络、进化计算之后新的智能计算研究领域和研究热点。
Artificial Immunology is a novel intelligent computing research field and research hotspot after artificial neural network and evolutionary computation.
提出了一种训练模糊神经网络的加速进化规划算法。
In this paper, a kind of accelerated evolutionary programming is presented to training the fuzzy neural networks.
本文提出了一种训练模糊神经网络的加速进化规则算法。
In this article, a kind of accelerated evolutionary programming is presented to training the fuzzy neural networks.
神经网络结构及权值优化属两级进化方法。
Simultaneity optimization for structure and weight distribution of neural network belongs to two class evolutionary method.
通过对不同情况算例的仿真，验证了神经网络目标预测算法和基于抗原进化免疫算法的正确性和有效性。
Correctness and validity of the neural network object forecast algorithm and immune algorithm with evaluated antigen are tested by the simulation of varies examples.
最后对机器人的路径规划进行了研究，将神经网络和免疫进化算法共同应用于机器人的路径规划。
Finally researches the path planning of robot, applies both neural network and immune evolution algorithm to the path planning of robot.
基于进化算法可有效解决神经网络设计和实现中存在的一些问题，使网络具有更优的性能。
Design and implementation of artificial neural networks based on evolutionary computation can lead to significantly better network performance.
基于进化算法可有效解决神经网络设计和实现中存在的一些问题，使网络具有更优的性能。
Design and implementation of artificial neural networks based on evolutionary computation can lead to significantly better network performance.
应用推荐