遗传算法在神经网络优化中的应用

把遗传算法和神经网络结合起来，形成以遗传算法与神经网络相结合的进化神经网络。介绍了遗传算法的基本原理。讨论了用遗传算法优化网络结构和基于遗传算法的神经网络权值优化问题。并通过实验仿真将该算法与BP算法进行比较，从而验证了该算法的可行性与有效性。     

基于遗传算法的神经网络性能优化

遗传算法是一种典型的进化算法。文中分析了遗传算法的特点和神经网络的特点,从而得出了把两种算法结合起来进行应用的思想。运用理论对比的方法,阐明了用遗传算法进行神经网络性能优化的原因,并得出结论,认为用遗传算法进行神经网络性能优化促使了神经网络更进一步的应用。阐述了遗传算法优化神经网络的两种主要方法,论述了遗传算法和神经网络的发展现状和将来的研究动向。     

基于知识模型的改进遗传算法

针对遗传算法个体进化缺乏明确导向的缺点,该文提出了一种基于知识模型的改进遗传算法,将遗传算法和神经网络有效结合起来,利用神经网络的学习功能。构造知识模型,用来引导群体中某些个体的进化。模拟实验验证了该算法的有效性。     

基于遗传算法的神经网络性能优化

遗传算法是一种典型的进化算法。文中分析了遗传算法的特点和神经网络的特点，从而得出了把两种算法结合起来进行应用的思想。运用理论对比的方法，阐明了用遗传算法进行神经网络性能优化的原因，并得出结论，认为用遗传算法进行神经网络性能优化促使了神经网络更进一步的应用。阐述了遗传算法优化神经网络的两种主要方法，论述了遗传算法和神经网络的发展现状和将来的研究动向。     

改进的遗传算法在优化BP网络权值中的应用

对遗传算法和BP神经网络的特点进行了比较,作为进化算法神经网络与遗传算法的目标相近而方法各异。阐述了遗传算法与神经网络结合的必要性。提出了一种改进的遗传算法优化BP神经网络的权值,用遗传算法的全局随机搜索能力弥补了神经网络容易陷入局部最优解的问题。同时,在遗传算法中改变传统的同代交叉机制,采用父代与子代进行交叉,避免了遗传算法过早丧失进化能力。     

基于统计学习理论优化感知器的遗传算法

本文提出一种基于统计学习理论优化感知器的遗传方法.该方法将遗传算法和神经网络相结合,通过统计学习理论指导遗传算法优化分类器的过程,避免了传统的感知器分类的偏向性、连接权的局部收敛性、误识率高等弱点;借助于遗传算法全局寻优的特点,使改进后的算法,具有自进化、自适应能力,以及很好的数据推广性能和抗干扰性,提高了神经网络的整体性能.与标准的SVM算法相比,具有更广阔的应用范围.     

基于自适应进化神经网络算法的入侵检测

针对目前多数入侵检测系统的低检测率问题,提出一种自适应进化神经网络算法AENNA。基于遗传算法和BP神经网络算法,利用模拟退火算法的概率突跳和局部搜索强的特性对遗传算法进行改进,采用双种群策略的遗传进化规则实现BP神经网络权值和结构的双重优化;通过对遗传算法的交叉算子与变异算子的改进,设计一种自适应的神经网络训练方法。实验结果表明,基于AENNA的入侵检测方法能够有效提高系统的检测率并降低误报率。     

用基于实数编码的自适应遗传算法进化神经网络

为了提高进化神经网络的速度,文章提出了一种基于实数编码方案的的遗传算法,该算法中采用了自适应变 异算子。用于求解ＸＯＲ问题,结果表明该算法具有很好的收敛性能。     

遗传算法在人工智能领域中的应用

该文介绍了遗传算法的基本概念、基本遗传算法的特点和基本遗传算法的求解步骤,同时也介绍了遗传算法在机器学习、并行处理、人工生命以及遗传算法与进化规则及进化策略的结合的发展动向,最后讨论了基于遗传算法的人工神经网络学习中的应用研究,具体论述了遗传算法在学习神经网络权重和学习神经网络拓扑结构的应用方法。     

交互式遗传算法基于NN 的个体适应度分阶段估计

针对交互式遗传算法中人的疲劳问题，提出一种基于神经网络(NN)的个体适应度分阶段估计方法，给出了神经网络估计进化个体适应度与人的评价之问的转换策略以及神经网络学习效果的评价指标，并分析了算法的复杂性．实例结果验证了该方法的有效性。     

Potential offspring production strategies: An improved genetic algorithm for global numerical optimization

In this paper, a sharing evolution genetic algorithms (SEGA) is proposed to solve various global numerical optimization problems. The SEGA employs a proposed population manager to preserve chromosomes which are superior and to eliminate those which are worse. The population manager also incorporates additional potential chromosomes to assist the solution exploration, controlled by the current solution searching status. The SEGA also uses the proposed sharing concepts for cross-over and mutation to prevent populations from falling into the local minimal, and allows GA to easier find or approach the global optimal solution. All the three parts in SEGA, including population manager, sharing cross-over and sharing mutation, can effective increase new born offspring’s solution searching ability. Experiments were conducted on CEC-05 benchmark problems which included unimodal, multi-modal, expanded, and hybrid composition functions. The results showed that the SEGA displayed better performance when solving these benchmark problems compared to recent variants of the genetic algorithms.     

基于多种群的强者进化遗传算法

针对简单遗传算法存在的问题,提出了一种基于多个种群的强者进化遗传算法SEGA。该算法首先利用多个异构子种群并行进化的结果初步确定较好解(强者),然后按照新的强者变异算子进一步寻找最优解。仿真结果表明,该算法能够提高收敛的速度和稳定性。     

A new evolutionary system for evolving artificial neural networks

This paper presents a new evolutionary system, i.e., EPNet, for evolving artificial neural networks (ANNs). The evolutionary algorithm used in EPNet is based on Fogel's evolutionary programming (EP). Unlike most previous studies on evolving ANN's, this paper puts its emphasis on evolving ANN's behaviors. Five mutation operators proposed in EPNet reflect such an emphasis on evolving behaviors. Close behavioral links between parents and their offspring are maintained by various mutations, such as partial training and node splitting. EPNet evolves ANN's architectures and connection weights (including biases) simultaneously in order to reduce the noise in fitness evaluation. The parsimony of evolved ANN's is encouraged by preferring node/connection deletion to addition. EPNet has been tested on a number of benchmark problems in machine learning and ANNs, such as the parity problem, the medical diagnosis problems, the Australian credit card assessment problem, and the Mackey-Glass time series prediction problem. The experimental results show that EPNet can produce very compact ANNs with good generalization ability in comparison with other algorithms.     

Soft computing in engineering design - A review

The present paper surveys the application of soft computing (SC) techniques in engineering design. Within this context, fuzzy logic (FL), genetic algorithms (GA) and artificial neural networks (ANN), as well as their fusion are reviewed in order to examine the capability of soft computing methods and techniques to effectively address various hard-to-solve design tasks and issues. Both these tasks and issues are studied in the first part of the paper accompanied by references to some results extracted from a survey performed for in some industrial enterprises. The second part of the paper makes an extensive review of the literature regarding the application of soft computing (SC) techniques in engineering design. Although this review cannot be collectively exhaustive, it may be considered as a valuable guide for researchers who are interested in the domain of engineering design and wish to explore the opportunities offered by fuzzy logic, artificial neural networks and genetic algorithms for further improvement of both the design outcome and the design process itself. An arithmetic method is used in order to evaluate the review results, to locate the research areas where SC has already given considerable results and to reveal new research opportunities.     

Solving optimization problems by parallel recombinative simulatedannealing on a parallel computer-an application to standard cellplacement in VLSI design

In this paper, parallel recombinative simulated annealing (PRSA), a hybrid method with features of simulated annealing and genetic algorithms, is examined. PRSA inherits the global convergence property from simulated annealing and the parallelism property from genetic algorithms. PRSA was implemented on a monoprocessor system as well as on a transputer. The algorithm, its parallel implementation, and its application to an NP-hard problem, namely standard cell placement in very large scale integration (VLSI) chip design, are described. PRSA was run for a large range of test cases. Since its performance depends on many parameters, the effects of parameter variations are studied in detail. Some important parameters are migration of individuals to other transputer nodes and selection strategies for constructing new populations. In comparison with simulated annealing and genetic algorithms, PRSA was found to produce better solutions.     

The truth will come to light: directions and challenges inextracting the knowledge embedded within trained artificial neuralnetworks

To date, the preponderance of techniques for eliciting the knowledge embedded in trained artificial neural networks (ANN's) has focused primarily on extracting rule-based explanations from feedforward ANN's. The ADT taxonomy for categorizing such techniques was proposed in 1995 to provide a basis for the systematic comparison of the different approaches. This paper shows that not only is this taxonomy applicable to a cross section of current techniques for extracting rules from trained feedforward ANN's but also how the taxonomy can be adapted and extended to embrace a broader range of ANN types (e,g., recurrent neural networks) and explanation structures. In addition we identify some of the key research questions in extracting the knowledge embedded within ANN's including the need for the formulation of a consistent theoretical basis for what has been, until recently, a disparate collection of empirical results.     

基于遗传算法的网络处理器异构资源映射方法研究

随着深亚微米工艺的迅速发展,现代网络处理器芯片广泛采用MPSoC(Multi-Processor System on Chip)体系结构实现,继而需要一种新的设计方法指导网络处理器体系结构设计.本文研究了网络处理器的设计方法,提出了一种基于遗传算法的网络应用到网络处理器异构硬件资源映射方法.该方法首先对网络处理器设计的问题空间进行分析,采用加权数据流进程网络描述网络应用,并参数化各种硬件资源,最后构建遗传算法来完成网络应用到异构硬件资源的映射,形成网络处理器体系结构设计方案.     

Scheduling algorithms for real-time computing systems admitting simulation models

A major requirement imposed on the operation of a real-time computing (RTC) system is that the deadlines for the operation of application programs must be met. The violation of an operational deadline leads to a failure of an RTC system. In this context, the problem arises of ensuring the required accuracy of estimating the execution time of application programs. An approach is developed for the design of iterative scheduling algorithms in which the execution times of application programs are estimated using simulation models with a different degree of detail, which ensures the required accuracy of estimating the execution time of programs. The approach can be used to design iterative algorithms of the following classes: genetic, evolutionary, simulated annealing, random-search, and locally optimal algorithms.     

MSN网络的优化问题研究

研究了由MSN节点组成的应用层组播网络,讨论了度约束最小直径生成树(D-MDST)问题,并给出了求解该问题的BCT算法。提出了一种新的生成树编码方法——过程控制编码,该编码将启发式算法与遗传算法结合起来且具有编码简单、译码方便、适用常规遗传算子等优点。给出了基于该种编码的遗传算法,并将BCT算法作为过程控制编码的译码器。仿真结果表明了该遗传算法的有效性。     

改进的IGA在建筑造型创新设计中的应用

交互式遗传算法(IGA)通过人机交互以用户对个体的评估代替传统的适应度函数,在艺术设计等偏向于人类主观感受的领域具有很高的应用价值和广泛的现实意义。文中针对IGA中人的疲劳问题,提出了将根据配对个体之间的相似度值自适应地确定交叉率的方法引入IGA。通过这种方法,可以提高遗传寻优计算的效率,加快IGA的收敛速度,有效缓解用户疲劳。将该方法应用于建筑造型的创新设计中,证明该方法的巨大潜力。