基于改进粒子群优化算法的新型小波神经网研究

本文提出了改进的粒子群优化算法（Improved Particle Swarm Optimization,IPSO）的新型BP 小波 神经网络,并且对非线性辨识问题进行了仿真实验．实验结果表明,基于改进的粒子群优化算法的BP 小波网 络不仅具有小波分析良好的局部特性以及神经网络的学习、分类能力,而且具有粒子群优化算法全局快速寻 优的特点．与简单的粒子群优化算法相比,该方法在收敛性和稳定性方面都有了较明显的提高,验证了它的 合理性和有效性．     

一种基于改进遗传算法的新型小波神经网研究

提出了一种基于改进遗传算法（Improved Genetic Algorithm , IGA）的新型BP小波神经网络，并通过异或问题和非线性辨识问题进行仿真实验。实验结果表明，基于改进遗传算法的BP小波网络不仅具有小波分析良好的局部特性以及神经网络的学习、分类能力，而且具有遗传算法全局快速寻优的特点，与简单遗传算法相比，在收敛快速性和稳定性方面都有了明显的改善。     

BP网络进化及其在雷达目标识别中的应用

针对常规ＢＰ神经网络的ＢＰ算法只能训练固定结构的神经网络,存在诸如易落入局部极值、没有引入提高泛化能力的训练机制等固有不足之处,以及一些神经网络进化算法的进化机制中存在的缺陷,本文提出一种ＢＰ神经网络进化算法,并用于高分辨雷达目标一维距离像的识别问题。实验结果表明,经所述方法优化后的神经网络结构简单、泛化能力优于ＢＰ算法和一些进化算法训练的网络。     

基于遗传算法优化神经网络的多用户检测

利用遗传算法全局搜索能力强和反向传播(BP)算法局部搜索速度快的特点,采取两段式训练方法,既避免陷入局部最小,又加快收敛速度。提出基于遗传算法优化神经网络权值的多用户检测算法。采用实数编码方式,将传统神经网络的能量函数作为适应度函数,选择算子选用轮盘赌算子,交叉算子选用单点交叉算子,变异算子选用正态变异算子。仿真结果表明,该算法的误码率、信干比和信道跟踪能力等方面的性能与传统前馈神经网络多用户检测算法相比均有一定的改善。     

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。     

混合GA-BP算法在机器人地面控制中的应用

为了增强移动机器人在动态环境中的学习和适应能力,提出一种基于GA-BP算法优化的神经网络的具有学习的机器人行为控制方法.单纯的BP算法有易陷入局部极小、收敛速度慢的缺点,根据遗传算法具有全局寻优的特点,将二者结合起来形成一种训练神经网络的混合GA-BP算法.实际的实验结果显示,提出的方法对机器人的学习和适应能力有很大的增强,并且提高了机器人行为的准确性和快速性,可以有效、可靠地运用于机器人地面控制,并可以方便地应用于其他方面.     

基于强化学习算法的神经网络模糊测试技术优化研究

现有神经网络模糊测试技术在测试样本生成阶段通常对初始样本进行随机变异,导致生成样本质量不高,从而测试覆盖率不高;针对以上问题,提出一种基于强化学习算法的神经网络模糊测试技术,将模糊测试过程建模为马尔可夫决策过程,在该模型中,测试样本被看作环境状态,不同的变异方法被看作可供选择的动作空间,神经元覆盖率被看作奖励反馈,使用强化学习算法来学习最优的变异策略,指导生成最优测试样本,使其能够获得最高的神经元覆盖率;通过与现有的主流神经网络模糊测试方法的对比实验表明,基于强化学习算法的神经网络模糊测试技术,可以提升在不同粒度下的神经元覆盖。     

基于MEA-BP的微波加热褐煤温度预测

对于微波干燥褐煤的温度采样数据具有多峰非平稳特性,采用小波阈值滤波能够较好地保留原始数据的细节信息。而直接使用反向传播（ BP）神经网络来建立对微波加热物料温度预测模型,具有预测精度低、收敛速度慢且容易陷入局部极小点等缺点。采用具有极强全局寻优能力的思维进化算法（ MEA）来优化BP（ MEA-BP）神经网络的初始权值和阈值。实验结果表明：经MEA-BP神经网络具有更高的预测精度和泛化能力,预测性能得到了显著的提高。     

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。     

一种结合演示数据和演化优化的强化学习方法

强化学习研究智能体如何从与环境的交互中学习最优的策略,以最大化长期奖赏。由于环境反馈的滞后性,强化学习问题面临巨大的决策空间,进行有效的搜索是获得成功学习的关键。以往的研究从多个角度对策略的搜索进行了探索,在搜索算法方面,研究结果表明基于演化优化的直接策略搜索方法能够获得优于传统方法的性能;在引入外部信息方面,通过加入用户提供的演示,可以有效帮助强化学习提高性能。然而,这两种有效方法的结合却鲜有研究。对用户演示与演化优化的结合进行研究,提出iNEAT+Q算法,尝试将演示数据通过预训练神经网络和引导演化优化的适应值函数的方式与演化强化学习方法结合。初步实验表明,iNEAT+Q较不使用演示数据的演化强化学习方法NEAT+Q有明显的性能改善。     

遗传算法自适应模糊神经网络控制

神经网络能够以任意精度逼近任意复杂的非线性关系,具有高度的自适应和自组织性,在解决高度非线性和严重不确定系统的控制方面具有巨大的潜力.但一般神经网络训练算法如BP算法训练速度慢,受初值影响大且易陷入局部极小点,该文提出了一种基于模糊神经网络的间接自校正控制系统,控制器以高斯隶属度函数的径向基函数（RBF）神经网络结构,利用改进的遗传算法（GA）对结构和参数进行同步优化,改进适应度函数指导搜索过程,在保证稳定情况下大大加快了收敛的速度.神经网络正向模型（NNP）利用弹性BP算法进行离线辨识,使得到的模型泛化性能好.     

Deep learning with particle filter for person re-identification

Person re-identification, having attracted much attention in the multimedia community, is still challenged by the accuracy and the robustness, as the images for the verification contain such variations as light, pose, noise and ambiguity etc. Such practical challenges require relatively robust and accurate feature learning technologies. We introduced a novel deep neural network with PF-BP(Particle Filter-Back Propagation) to achieve relatively global and robust performances of person re-identification. The local optima in the deep networks themselves are still the main difficulty in the learning, in despite of several advanced approaches. A novel neural network learning, or PF-BP, was first proposed to solve the local optima problem in the non-convex objective function of the deep networks. When considering final deep network to learn using BP, the overall neural network with the particle filter will behave as the PF-BP neural network. Also, a max-min value searching was proposed by considering two assumptions about shapes of the non-convex objective function to learn on. Finally, a salience learning based on the deep neural network with PF-BP was proposed to achieve an advanced person re-identification. We test our neural network learning with particle filter aimed to the non-convex optimization problem, and then evaluate the performances of the proposed system in a person re-identification scenario. Experimental results demonstrate that the corresponding performances of the proposed deep network have promising discriminative capability in comparison with other ones.

     

基于改进型遗传算法的前馈神经网络优化设计

阐明了遗传算法和神经网络结合的可行性，提出了一种改进的面向神经网络权值学习的遗传算法。通过对XOR问题的实验，显示出其快速学习网络权值的能力，且能摆脱局部极值的困扰和初始权值的限制，从各方面都表现出优于标准遗传算法和BP算法的性能。     

Hybrid back-propagation training with evolutionary strategies

This work presents a hybrid algorithm for neural network training that combines the back-propagation (BP) method with an evolutionary algorithm. In the proposed approach, BP updates the network connection weights, and a ( \(1+1\) ) Evolutionary Strategy (ES) adaptively modifies the main learning parameters. The algorithm can incorporate different BP variants, such as gradient descent with adaptive learning rate (GDA), in which case the learning rate is dynamically adjusted by the stochastic ( \(1+1\) )-ES as well as the deterministic adaptive rules of GDA; a combined optimization strategy known as memetic search. The proposal is tested on three different domains, time series prediction, classification and biometric recognition, using several problem instances. Experimental results show that the hybrid algorithm can substantially improve upon the standard BP methods. In conclusion, the proposed approach provides a simple extension to basic BP training that improves performance and lessens the need for parameter tuning in real-world problems.     

基于局部收敛权阵进化的BP神经网络MapReduce训练

为提高大样本集情况下BP神经网络的训练效率,提出了一种基于局部收敛权阵进化的BP神经网络MapReduce训练方法,以各Map任务基于其输入数据分片训练产生的局部收敛权阵作为初始种群,在Reduce任务中通过种群进化,选取适应度最高的权阵作为Map任务下一轮训练的初始权阵,直至该权阵对所有输入数据分片收敛。实验结果表明,与现有方法相比,该方法可有效避免MapReduce训练BP神经网络时容易陷入局部收敛的问题,并大大减少训练时间。     

On Model-Based Evolutionary Computation

 Traditional evolutionary computing techniques use an explicit fitness function – mathematical or simulated – to derive a solution to a problem from a population of individuals, over a number of generations. In this paper an approach which allows such techniques to be used on problems in which evaluations are costly, which cannot be expressed formally, or which are difficult to simulate, is examined. A neural network is trained using example individuals with the explicit fitness and the resulting model of the fitness function is then used by the evolutionary algorithm to find a solution. It is shown that the approach is effective over a small range of function types in comparison to the traditional approach when limited training data is available. An iterative step is then added whereby after a number of generations the current best individual in a population is evaluated directly on the explicit fitness function. The individual and its “real” fitness are then added to the training data and the neural network is re-trained to improve its approximation of the fitness function. It is shown that in this way the performance of the model-based architecture is greatly improved on more rugged/complex landscapes without a large increase in the amount of training data required.     

Application of temporal difference learning rules in short‐term traffic flow prediction

Studying dynamic behaviours of a transportation system requires the use of the system mathematical models as well as prediction of traffic flow in the system. Therefore, traffic flow prediction plays an important role in today's intelligent transportation systems. This article introduces a new approach to short‐term daily traffic flow prediction based on artificial neural networks. Among the family of neural networks, multi‐layer perceptron (MLP), radial basis function (RBF) neural network and wavenets have been selected as the three best candidates for performing traffic flow prediction. Moreover, back‐propagation (BP) has been adapted as the most efficient learning scheme in all the cases. It is shown that the coefficients produced by temporal signals improve the performance of the BP learning (BPL) algorithm. Temporal signals provide researchers with a new model of temporal difference BP learning algorithm (TDBPL). The capability and performance of TDBPL algorithm are examined by means of simulation in order to prove that the wavelet theory, with its multi‐resolution ability in comparison to RBF neural networks, is a suitable algorithm in traffic flow forecasting. It is also concluded that despite MLP applications, RBF neural networks do not provide negative forecasts. In addition, the local minimum problems are inevitable in MLP algorithms, while RBF neural networks and wavenet networks do not encounter them.     

基于改进型BP神经网络的手部动作识别

对手部动作进行模式识别,首先将采集到的肌电信号进行降噪处理,选择时域分析法中的方差算法对采集信号进行特征提取。将特征信号进行归一化处理,实验发现普通BP神经网络分类器出现学习速率慢,泛化能力较差,不同动作识别准确率差别较大等问题。针对以上问题,提出了一种改进型BP神经网络,将神经网络输入数据进行人工升维处理,并对网络学习速率慢的原因进行理论推导,然后引入交叉熵代价函数并对其进行正则化处理,以提高网络的泛化能力以及网络的识别准确率。实验结果表明,改进型BP神经网络的学习速率、泛化能力以及动作分类的准确率均优于普通网络,识别准确率平均为94.34%。     

A self-organizing HCMAC neural-network classifier

This paper presents a self-organizing hierarchical cerebellar model arithmetic computer (HCMAC) neural-network classifier, which contains a self-organizing input space module and an HCMAC neural network. The conventional CMAC can be viewed as a basis function network (BFN) with supervised learning, and performs well in terms of its fast learning speed and local generalization capability for approximating nonlinear functions. However, the conventional CMAC has an enormous memory requirement for resolving high-dimensional classification problems, and its performance heavily depends on the approach of input space quantization. To solve these problems, this paper presents a novel supervised HCMAC neural network capable of resolving high-dimensional classification problems well. Also, in order to reduce what is often trial-and-error parameter searching for constructing memory allocation automatically, proposed herein is a self-organizing input space module that uses Shannon's entropy measure and the golden-section search method to appropriately determine the input space quantization according to the various distributions of training data sets. Experimental results indicate that the self-organizing HCMAC indeed has a fast learning ability and low memory requirement. It is a better performing network than the conventional CMAC for resolving high-dimensional classification problems. Furthermore, the self-organizing HCMAC classifier has a better classification ability than other compared classifiers.     

Prediction of cooling efficiency of forced-air precooling systems based on optimized differential evolution and improved BP neural network

This paper proposes an approach to predict the efficiency of forced-air cooling of fresh apples that combines the optimized differential evolution (DE) algorithm and the back-propagation (BP) neural network algorithm. First, to balance population diversity and fast convergence, the individual mutation operation of the basic DE algorithm was optimized by dividing the entire population into two equal parts according to the fitness value of individuals, and DE-best-1 and DE-current-to-rand-1 are used as individual mutation operations for the superior- and inferior-part individuals, respectively. Moreover, the selection operation of basic DE was also changed by using a crowding scheme, which helps maintain population diversity and discover more regions containing the global optima. Second, an optimized DE-BP neural network model was established by using the optimized DE to determine the initial weights and thresholds of the BP neural network to avoid being trapped in local minima, following which the effect of input parameters on the network output was subjected to a comprehensive sensitivity analysis based on the trained neural network. The results show that the optimized DE-BP model accurately predicts the efficiency with which apples are cooled. Furthermore, the airflow velocity and total opening area have a significant negative correlation with the average apple temperature and a positive correlation with the cooling rate of the apples. Finally, the most important factor influencing the cooling efficiency of the pre-cooling system is the total opening area of the ventilated packaging.