An efficient hybrid learning algorithm for neural network–based speech recognition systems on FPGA chip

This paper implemented an artificial neural network (ANN) on a field programmable gate array (FPGA) chip for Mandarin speech measurement and recognition of nonspecific speaker. A three-layer hybrid learning algorithm (HLA), which combines genetic algorithm (GA) and steepest descent method, was proposed to fulfill a faster global search of optimal weights in ANN. Some other popular evolutionary algorithms, such as differential evolution, particle swarm optimization and improve GA, were compared to the proposed HLA. It can be seen that the proposed HLA algorithm outperforms the other algorithms. Finally, the designed system was implemented on an FPGA chip with an SOC architecture to measure and recognize the speech signals.     

改进人工蜂群优化BP神经网络的分类研究

针对BP神经网络对初始权重敏感,容易陷入局部最优,人工蜂群算法局部搜索能力和开发能力相对较弱等问题,提出一种基于改进人工蜂群和反向传播的神经网络训练方法。引进差分进化思想改进人工蜂群算法,并对跟随蜂的搜索行为进行更准确的描述。用改进的人工蜂群全局搜索神经网络的初始权重,防止神经网络陷入局部最优。用新的方法对神经网络训练进行分类。实验结果表明,该算法相对于标准的BP神经网络,有效提高了分类正确率,泛化能力较强。     

基于遗传模糊神经网络的煤气鼓风机故障诊断

为充分利用遗传算法的全局搜索能力和BP算法的局部搜索能力,提出了基于遗传算法的遗传模糊神经网络模型,研究了故障特征参数模糊化处理和利用遗传算法优化神经网络权重的方法,加快了网络收敛速度,提高了收敛精度.在煤气鼓风机故障诊断中的应用表明,遗传模糊神经网络克服了BP算法中存在的网络学习收敛速度慢,以及容易陷入局部极小的问题,有效提高了故障诊断的精度.     

Design of robotic visual servo control based on neural network and genetic algorithm

A new visual servo control scheme for a robotic manipulator is presented in this paper, where a back propagation (BP) neural network is used to make a direct transition from image feature to joint angles without requiring robot kinematics and camera calibration. To speed up the convergence and avoid local minimum of the neural network, this paper uses a genetic algorithm to find the optimal initial weights and thresholds and then uses the BP algorithm to train the neural network according to the data given. The proposed method can effectively combine the good global searching ability of genetic algorithms with the accurate local searching feature of BP neural network. The Simulink model for PUMA560 robot visual servo system based on the improved BP neural network is built with the Robotics Toolbox of Matlab. The simulation results indicate that the proposed method can accelerate convergence of the image errors and provide a simple and effective way of robot control.     

A filter model for feature subset selection based on genetic algorithm

This paper describes a novel feature subset selection algorithm, which utilizes a genetic algorithm (GA) to optimize the output nodes of trained artificial neural network (ANN). The new algorithm does not depend on the ANN training algorithms or modify the training results. The two groups of weights between input-hidden and hidden-output layers are extracted after training the ANN on a given database. The general formula for each output node (class) of ANN is then generated. This formula depends only on input features because the two groups of weights are constant. This dependency is represented by a non-linear exponential function. The GA is involved to find the optimal relevant features, which maximize the output function for each class. The dominant features in all classes are the features subset to be selected from the input feature group.     

扩散遗传算法及其应用研究

针对遗传算法在局部搜索能力方面的缺陷,提出了一种基于扩散算子的遗产算法(简称扩散遗产算法)。该算法中包含的扩散算子是变异算子,其主要作用是在遗传搜索中进行局部搜索。用扩散遗传算法和实数编码遗传算法分别训练用于解XOR问题的神经网络,对比结果表明,论文提出的算法兼具强的全局搜索能力和局部搜索能力,因此,该算法可以不借助其它局部搜索算法而单独作为神经网络训练算法,从而简化训练算法,提高训练效率。该算法对提高遗传算法搜索效率和求解精度具有重要的意义。     

基于FLANN的称重传感器动态补偿方法

为满足快速称重的要求,结合遗传算法寻优速度快和函数联接型神经网络(FLANN)有较强的函数逼近能力的优点,设计了一种基于遗传算法优化的FLANN补偿器,实现对称重传感器的动态特性补偿。采用遗传算法优化FLANN的连接权值。仿真表明:阶跃响应时间快,且超调量小,有效地提高了称重传感器的动态响应过程,且方法简单,易于工程实现,具有实用价值。     

气体传感器阵列常用模式识别算法

模式识别在气体传感器阵列的测量中占有举足轻重的地位。介绍了k近邻法、聚类分析、判别函数分析、反向传播人工神经网络、主元分析法、概率神经网、学习向量量化、自组织映射、自适应共振网、遗传算法等气体传感器阵列常用模式识别算法的原理和特点。同时,指出了在应用中模式识别算法选择和评价的标准。     

基于小生境-遗传算法优化的新型BP模型

为解决传统BP神经网络模型易陷入局部极小点、网络结构不稳定、收敛速度慢等问题,提出了一个小生境遗传算法优化的BP神经网络模型。该网络模型借助BP神经网络的非线性映射和学习联想能力和小生境遗传算法的搜索能力,利用小生境遗传算法的选择、交叉、变异及小生境淘汰等操作,来对BP神经网络的初始权值和阈值进行优化,同时使用BP算法来训练该模型,从而有效地解决了网络初值不合理的问题,提高了网络收敛速度、稳定性。实验证明：与传统方法相比,该模型具有很强的可行性和有效性。     

Mutation-based genetic neural network

Evolving gradient-learning artificial neural networks (ANNs) using an evolutionary algorithm (EA) is a popular approach to address the local optima and design problems of ANN. The typical approach is to combine the strength of backpropagation (BP) in weight learning and EA's capability of searching the architecture space. However, the BP's "gradient descent" approach requires a highly computer-intensive operation that relatively restricts the search coverage of EA by compelling it to use a small population size. To address this problem, we utilized mutation-based genetic neural network (MGNN) to replace BP by using the mutation strategy of local adaptation of evolutionary programming (EP) to effect weight learning. The MGNN's mutation enables the network to dynamically evolve its structure and adapt its weights at the same time. Moreover, MGNN's EP-based encoding scheme allows for a flexible and less restricted formulation of the fitness function and makes fitness computation fast and efficient. This makes it feasible to use larger population sizes and allows MGNN to have a relatively wide search coverage of the architecture space. MGNN implements a stopping criterion where overfitness occurrences are monitored through "sliding-windows" to avoid premature learning and overlearning. Statistical analysis of its performance to some well-known classification problems demonstrate its good generalization capability. It also reveals that locally adapting or scheduling the strategy parameters embedded in each individual network may provide a proper balance between the local and global searching capabilities of MGNN.     

Artificial neural networks with evolutionary instance selection for financial forecasting

In this paper, I propose a genetic algorithm (GA) approach to instance selection in artificial neural networks (ANNs) for financial data mining. ANN has preeminent learning ability, but often exhibit inconsistent and unpredictable performance for noisy data. In addition, it may not be possible to train ANN or the training task cannot be effectively carried out without data reduction when the amount of data is so large. In this paper, the GA optimizes simultaneously the connection weights between layers and a selection task for relevant instances. The globally evolved weights mitigate the well-known limitations of gradient descent algorithm. In addition, genetically selected instances shorten the learning time and enhance prediction performance. This study applies the proposed model to stock market analysis. Experimental results show that the GA approach is a promising method for instance selection in ANN.     

一种基于遗传优化的神经网络水印

提出一种新的遗传算法和神经网络彩色图像水印研究,在检测水印的过程中,利用遗传算法来优化BP神经网络的权值矩阵与初值,构建出内在的隐含关系,然后利用训练好的BP神经网络来融合提取水印.实验证明该算法保持不可觉察性,并且水印的鲁棒性比BP神经网络的更强.     

基于注意力模型的混合学习算法

为了解决传统BP(back-propagation)算法收敛速度慢,训练得到的网络性能较差的问题,在借鉴生理学中"选择性注意力模型"的基础上,将遗传算法与误差放大的BP学习算法进行了有机的融合,提出了基于注意力模型的快速混合学习算法.该算法的核心在于将单独的BP训练过程划分为许多小的切片,并对每个切片进行误差放大的训练和竞争淘汰机制的选择.通过发现收敛速率较快的个体和过滤陷入局部极值的个体,来保证网络训练的成功率和实现快速向全局最优区域逼近的目的.仿真结果表明,该算法有效地解决了传统BP算法中由于初始权值的随机性造成的训练失败问题,并能有效解决饱和区域引起的后期训练缓慢问题,在不增加网络隐层节点数的情况下,显著地提高了网络的收敛精度和泛化能力.这将使神经网络在众多实际的分类问题上具有更广泛的应用前景.     

Determining the Natural Frequency of Cantilever Beams Using ANN and Heuristic Search

An artificial neural network (ANN) is used to model the frequency of the first mode, using the beam length, the moment of inertia, and the load applied on the beam as input parameters on a database of 100 samples. Three different heuristic optimization methods are used to train the ANN: genetic algorithm (GA), particle swarm optimization algorithm and imperialist competitive algorithm. The suitability of these algorithms in training ANN is determined based on accuracy and runtime performance. Results show that, in determining the natural frequency of cantilever beams, the ANN model trained using GA outperforms the other models in terms of accuracy.     

Prediction of first lactation 305-day milk yield in Karan Fries dairy cattle using ANN modeling

In this paper, an artificial neural network (ANN) model is proposed to predict the first lactation 305-day milk yield (FLMY305) using partial lactation records pertaining to the Karan Fries (KF) crossbred dairy cattle. A scientifically determined optimum dataset of representative breeding traits of the cattle is used to develop the model.Several training algorithms, viz., (i) gradient descent algorithm with adaptive learning rate; (ii) Fletcher–Reeves conjugate gradient algorithm; (iii) Polak–Ribiére conjugate gradient algorithm; (iv) Powell–Beale conjugate gradient algorithm; (v) Quasi-Newton algorithm with Broyden, Fletcher, Goldfarb, and Shanno (BFGS) update; and (vi) Levenberg–Marquardt algorithm with Bayesian regularization; along with various network architectural parameters, i.e., data partitioning strategy, initial synaptic weights, number of hidden layers, number of neurons in each hidden layer, activation functions, regularization factor, etc., are experimentally investigated to arrive at the best model for predicting the FLMY305.Also, a multiple linear regression (MLR) model is developed for the milk-yield prediction. The performances of ANN and MLR models are compared to assess the relative prediction capability of the former model.It emerges from this study that the performance of ANN model seems to be slightly superior to that of the conventional regression model. Hence, it is recommended that the ANNs can potentially be used as an alternative technique to predict FLMY305 in the KF cattle.     

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。     

遗传BP神经网络在网络流量预测中的应用

由于BP神经网络本质上采用的是梯度下降算法,具有收敛速度慢、容易陷入局部极小点等缺陷.针对这种情况,用具有良好全局搜索能力的遗传算法来改进BP神经网络模型,对神经网络的初始权值和阈值进行优化.仿真结果表明,遗传BP神经网络具有良好的预测效果,预测精度比传统的BP神经网络要高,误差更小,说明了遗传BP神经网络对网络流量预测是高效可行的.     

Developing soft sensors using hybrid soft computing methodology: a neurofuzzy system based on rough set theory and genetic algorithms

This paper presents a hybrid soft computing modeling approach, a neurofuzzy system based on rough set theory and genetic algorithms (GA). To solve the curse of dimensionality problem of neurofuzzy system, rough set is used to obtain the reductive fuzzy rule set. Both the number of condition attributes and rules are reduced. Genetic algorithm is used to obtain the optimal discretization of continuous attributes. The fuzzy system is then represented via an equivalent artificial neural network (ANN). Because the initial parameter of the ANN is reasonable, the convergence of the ANN training is fast. After the rules are reduced, the structure size of the ANN becomes small, and the ANN is not fully weight-connected. The neurofuzzy approach based on RST and GA has been applied to practical application of building a soft sensor model for estimating the freezing point of the light diesel fuel in fluid catalytic cracking unit.     

增强现实系统中磁力跟踪器的校正

提出了利用BP神经网络对跟踪器进行校正。针对神经网络训练速度慢、容易陷入局部极值的情况，首先利用具有良好全局搜索能力的遗传算法来优化BP神经网络的各层初始权值和阈值，为后续神经网络的搜索定位出一个优化的搜索空间。实验结果表明，利用该遗传神经网络方法进行跟踪器校正，能够显著提高增强现实系统的精度，有助于提高增强现实系统的真实感。     

Hybrid genetic algorithms for structural reliability analysis

The traditional genetic algorithms (GA) involve step-by-step numerical iterations for searching the minimum reliability index of a structural system, and therefore require a relatively long computation time. In practice the size of a design problem can be very large, the limit state functions are usually implicit in terms of the random variables. When using the traditional genetic algorithms, one can encounter problems with the immense effort required in coding ones own finite element code (or for integration with other commercial finite element software) when using the traditional genetic algorithms. For convenient practical applications of the GA in engineering, two new GA methods, namely, a hybrid GA method consisting of artificial neural network (ANN) and a hybrid GA method consisting of ANN and Monte Carlo simulation with importance sampling are proposed in the present study. A distinctive feature of these proposed methods is the introduction of an explicit approximate limit state function. The explicit formulation of the approximate limit state function is derived by using the parameters of the ANN model. By introducing the derived approximate limit state function, the failure probability can be easily calculated, practically when the limit state functions are not explicitly known. These proposed methods are investigated and their accuracy and efficiency are demonstrated using numerical examples. Finally, some important parameters in these proposed methods are also discussed.