Ensemble of Evolving Neural Networks in Classification

The ensemble of evolving neural networks, which employs neural networks and genetic algorithms, is developed for classification problems in data mining. This network meets data mining requirements such as smart architecture, user interaction, and performance. The evolving neural network has a smart architecture in that it is able to select inputs from the environment and controls its topology. A built-in objective function of the network offers user interaction for customized classification. The bagging technique, which uses a portion of the training set in multiple networks, is applied to the ensemble of evolving neural networks in order to improve classification performance. The ensemble of evolving neural networks is tested by various data sets and produces better performance than both classical neural networks and simple ensemble methods.     

遗传算法优化前向神经网络结构和权重矢量

提出了新的遗传算法优化设计前向神经网络的结构和权重矢量。这种新方法的创新在于：二值码串和实值码串的混合编码方法即保留了传统遗传法的优点,又具有遗传编程和跗策略的优点。     

基于局部进化的Hopfield神经网络的优化计算方法

提出一种基于局部进化的Hopfield神经网络优化计算方法，该方法将遗传算法和Hopfield神经网络结合在一起，克服了Hopfield神经网络易收敛到局部最优值的缺点，以及遗传算法收敛速度慢的缺点。该方法首先由Hopfield神经网络进行状态方程的迭代计算降低网络能量，收敛后的Hopfield神经网络在局部范围内进行遗传算法寻优，以跳出可能的局部最优值陷阱，再由Hopfield神经网络进一步迭代优化。这种局部进化的Hopfield神经网络优化计算方法尤其适合于大规模的优化问题，对图像分割问题和规模较大的200城市旅行商问题的优化计算结果表明，其全局收敛率和收敛速度明显提高。     

基于实数编码遗传算法的神经网络优化设计

提出一种基于综合控制策略的改进的实数编码遗传算法,用该算法对前向神经网络的结构及权值进行优化。通过实验结果表明,该算法能快速有效的确定网络的结构及权值。     

Designing Polymer Blends Using Neural Networks, Genetic Algorithms, and Markov Chains

In this paper we present a new technique to simulate polymer blends that overcomes the shortcomings in polymer system modeling. This method has an inherent advantage in that the vast existing information on polymer systems forms a critical part in the design process. The stages in the design begin with selecting potential candidates for blending using Neural Networks. Generally the parent polymers of the blend need to have certain properties and if the blend is miscible then it will reflect the properties of the parents. Once this step is finished the entire problem is encoded into a genetic algorithm using various models as fitness functions. We select the lattice fluid model of Sanchez and Lacombe (J. Polym. Sci. Polym. Lett. Ed., vol. 15, p. 71, 1977), which allows for a compressible lattice. After reaching a steady-state with the genetic algorithm we transform the now stochastic problem that satisfies detailed balance and the condition of ergodicity to a Markov Chain of states. This is done by first creating a transition matrix, and then using it on the incidence vector obtained from the final populations of the genetic algorithm. The resulting vector is converted back into a population of individuals that can be searched to find the individuals with the best fitness values. A high degree of convergence not seen using the genetic algorithm alone is obtained. We check this method with known systems that are miscible and then use it to predict miscibility on several unknown systems.     

基于进化神经网络的模拟电路故障诊断

基于人工神经网络的智能故障诊断系统作为人工智能技术在模拟电路故障诊断领域的应用,在实践中取得了一定的成效.但由于容差和非线性特性使得模拟电路的故障诊断趋于复杂化,以及诊断系统中神经网络的拓扑结构难以确定,因此,针对上述局限,提出了模拟电路故障诊断的进化神经网络方法;文中详细的阐述了进化神经网络的构成方式,提出了把网络的结构和权值分级进化的方法,并在两级进化的过程中使用不同的适应度函数及改进的遗传算法.举例说明诊断系统的具体实现方法,仿真结果表明,在相同的精度要求下,该算法的训练时间远小于普通的进化神经网络,对模拟电路的故障诊断有一定的实际意义.     

Feedback Approximation of the Stochastic Growth Model by Genetic Neural Networks

A direct numerical optimization method is developed to approximate the one-sector stochastic growth model. The feedback investment policy is parameterized as a neural network and trained by a genetic algorithm to maximize the utility functional over the space of time-invariant investment policies. To eliminate the dependence of training on the initial conditions, at any generation, the same stationary investment policy (the same network) is used to repeatedly solve the problem from differing initial conditions. The fitness of a given policy rule is then computed as the sum of payoffs over all initial conditions. The algorithm performs quite well under a wide set of parameters. Given the general purpose nature of the method, the flexibility of neural network parametrization and the global nature of the genetic algorithm search, it can be easily extended to tackle problems with higher dimensional nonlinearities, state spaces and/or discontinuities.     

基于小波网络和多模块网络的数字识别

本文研究一种新的数字识别方法,这种方法用小波神经网络抽取特征、用多模块结构神经网络作模式分类器。小波分解的函数近似能力和人工神经网络的学习能力结合起来形成的小波神经网络,有着良好的特征描述性能,可用作特征抽取工具。多模块结构的神经网络将一个k类的模式分类问题转换为k个互相独立的2类分类问题。这种结构将一个复杂的分类问题化解为多个简单的分类问题,各个模块互相并联,各自负责一种模式的识别。用这种修改过的多模块结构网络的BP训练方法,可加速训练和提高训练精度,并且各模块可互相独立地进行训练。用美国NIST数字样本进行训练及测试,结果良好。这种方法可用于更广泛的平面图形识别。     

基于免疫算法的前馈神经网络权值设计

提出了一种基于免疫算法的前馈神经网络设计方法(ImmuneFeed-forwardNeuralNetwork,INN),用于实现前馈神经网络权值空间的搜索。初步实验结果显示免疫算法具有快速学习网络权值的和脱离局部极小点的能力。     

神经网络中的粒子权重计算

讨论了将粒子信息存入神经网络的机制,以加速网络训练,提高清晰度,提出了语言权重的GNN及语言算法规则。GNN比标准BP网络需要少训练时间来学习已矧问题,同时知识的表示更易于理解。     

遗传优化模糊神经网络在组合导航系统中的应用

组合导航系统中,传统的多传感器数据融合算法存在着非线性、计算误差、维数灾难和模型误差等问题.遗传优化模糊神经网络不仅具有模糊神经网络的表达近似与定性知识,较强的学习和非线性表达等能力,而且具有遗传算法的全局搜索能力,是一种有效的数据融合算法.本文将之应用于组合导航系统中,仿真结果证明了该算法的有效性.     

Evolving Fault-Tolerant Neural Networks

In this paper, genetic algorithm is used to help improve the tolerance of feedforward neural networks against an open fault. The proposed method does not explicitly add any redundancy to the network, nor does it modify the training algorithm. Experiments show that it may profit the fault tolerance as well as the generalisation ability of neural networks.     

一种神经网络辨识的混合学习算法

文章提出了一种神经网络辨识的混合学习算法。采用具有递阶结构的遗传算法来获得神经网络拓扑结构和连接权值的全局次优解,之后由BP算法来进一步调整神经网络的连接权值,从而实现神经网络的自动优化设计。仿真结果表明,所得的神经网络结构简单、精度高,并具有良好的泛化能力。     

Approximate Match of Rules Using Backpropagation Neural Networks

This paper presents a method for approximate match of first-order rules with unseen data. The method is useful especially in case of a multi-class problem or a noisy domain where unseen data are often not covered by the rules. Our method employs the Backpropagation Neural Network for the approximation. To build the network, we propose a technique for generating features from the rules to be used as inputs to the network. Our method has been evaluated on four domains of first-order learning problems. The experimental results show improvements of our method over the use of the original rules. We also applied our method to approximate match of propositional rules converted from an unpruned decision tree. In this case, our method can be thought of as soft-pruning of the decision tree. The results on multi-class learning domains in the UCI repository of machine learning databases show that our method performs better than standard C4.5's pruned and unpruned trees.     

基于粗糙集的进化神经网络入侵检测系统研究

针对目前实时入侵检测系统所处理的网络数据具有的非线性和高维的特点,提出基于粗糙集理论的进化神经网络入侵检测方法。对网络中截获的数据,利用粗糙集属性约简方法对其属性集进行约简,得到影响分类精度的重要属性。把约简后形成的训练样本进行数值化和归一化处理,作为神经网络的输入数据,再利用遗传算法较强的宏观搜索能力和全局寻优的特点,优化神经网络权值,并在此基础上进行神经网络学习,从而建立入侵检测系统的优化分析模型。实验结果表明,该算法学习速度快,有效提高了入侵检测系统的检测效率。     

进化神经网络中的变异算子研究

针对进化神经网络中遗传算法收敛速度慢和容易早熟这两个难题,提出了一个启发性的变异算子.该算子采用了自适应的变异率和启发式的变异位的选择策略.在多代无进化时,通过提高变异率扩大搜索范围,同时减小变异量进行更细致的搜索.求解XOR问题的实验表明,该算法既具有很快的收敛速度又能自动维持群体的多样性.     

Evolving Neuro-Controllers for a Dynamic System Using Structured Genetic Algorithms

This paper describes the application of the Structured Genetic Algorithm (sGA) to design neuro-controllers for an unstable physical system. In particular, the approach uses a single unified genetic process to automatically evolve complete neural nets (both architectures and their weights) for controlling a simulated pole-cart system. Experimental results demonstrate the effectiveness of the sGA-evolved neuro-controllers for the task—to keep the pole upright (within a specified vertical angle) and the cart within the limits of the given track.     

Segmentation of MR and CT Images Using a Hybrid Neural Network Trained by Genetic Algorithms

A novel hybrid neural network trained by the genetic algorithms is presented. Genetic algorithms are used to improve the neural net's classification performance while minimizing the number of nodes. Each node of the network forms a closed region in the input space. The closed regions, which are formed by the nodes, intersect each other. The performance of the proposed hybrid neural network is compared with the multilayer perceptron, and the restricted Coulomb energy network for the segmentation of MR and CT head images. Experimental results show that the proposed neural network gives the best classification performance with a small number of nodes in short training times.     

基于遗传算法的神经网络学习方法

本文阐述了将遗传算法用于神经网络权值学习和训练的原理和万法,并详述了神经网络权值学习和训练中遗传算法的具体实现过程。     

Exchange-Rates Forecasting: A Hybrid Algorithm Based on Genetically Optimized Adaptive Neural Networks

The use of neural networks trained by a new hybrid algorithm is employed on forecasting the Greek Foreign Exchange-Rate Market. Four major currencies, namely the U.S. Dollar (USD), the Deutsche Mark (DEM), the French Franc (FF) and the British Pound (GBP), versus the Greek Drachma, were used as experimental data. The proposed algorithm combines genetic algorithms and a training method based on the localized Extended Kalman Filter (EKF), in order to evolve the structure and train Multi-Layered Perceptron (MLP) neural networks. The goal of this effort is to predict, as accurately as possible, exchange-rates future behavior. Simulation results show that the method gives highly successful results, while the diversification of the structure between the four currencies has no effect on the performance.