Description: 基于GMM的概率神经网络PNN具有良好的泛化能力，快速的学习能力，易于在线更新,并具有统计学的贝叶斯估计理论基础，已成为一种解决像说话人识别、文字识别、医疗图像识别、卫星云图识别等许多实际困难分类问题的很有效的工具。而且PNN不但具有GMM的大部分优点，还具有许多GMM没有的优点，如强鲁棒性，需要更少的训练语料，可以和其他网络其他理论无缝整合等。-GMM based probabilistic neural network PNN good generalization ability, the ability to learn fast, easy online updates, and with the Bayesian statistical theory based on estimates, and has become a solution as speaker recognition, text recognition, medical image recognition, satellite images and other real recognition when difficulties classification of very effective tool. But GMM PNN is not only the most advantages, but also has many advantages GMM not as strong robustness, require less training corpus, and other networks to other theories, such as seamless integration. Platform: |
Size: 7158 |
Author:姜正茂 |
Hits:
Description: 基于GMM的概率神经网络PNN具有良好的泛化能力，快速的学习能力，易于在线更新,并具有统计学的贝叶斯估计理论基础，已成为一种解决像说话人识别、文字识别、医疗图像识别、卫星云图识别等许多实际困难分类问题的很有效的工具。而且PNN不但具有GMM的大部分优点，还具有许多GMM没有的优点，如强鲁棒性，需要更少的训练语料，可以和其他网络其他理论无缝整合等。-GMM based probabilistic neural network PNN good generalization ability, the ability to learn fast, easy online updates, and with the Bayesian statistical theory based on estimates, and has become a solution as speaker recognition, text recognition, medical image recognition, satellite images and other real recognition when difficulties classification of very effective tool. But GMM PNN is not only the most advantages, but also has many advantages GMM not as strong robustness, require less training corpus, and other networks to other theories, such as seamless integration. Platform: |
Size: 7168 |
Author:姜正茂 |
Hits:
Description: An Improved PSO Algorithm to Optimize BP Neural Network
Abstract
This paper presents a new BP neural network
algorithm which is based on an improved particle swarm
optimization (PSO) algorithm. The improved PSO (which
is called IPSO) algorithm adopts adaptive inertia weight
and acceleration coefficients to significantly improve the
performance of the original PSO algorithm in global
search and fine-tuning of the solutions. This study uses the
IPSO algorithm to optimize authority value and threshold
value of BP nerve network and IPSO-BP neural network
algorithm model has been established. The results
demonstrate that this model has significant advantages
inspect of fast convergence speed, good generalization
ability and not easy to yield minimal local results Platform: |
Size: 252928 |
Author:dasu |
Hits:
Description: 为了更好了解遗传神经网络在系统中的对比效果，我们以室内温度控制为例，设室内的温度控制目标为18℃（20℃），其他参数保持不变的情况下，分别按照单独神经网络和基于遗传算法优化后的神经网络控制进行仿真实验.仿真结果表明，上述应用遗传算法优化的神经网络是非常有效的，通过运用遗传算法对神经网络进行优化，使其具有良好的泛化能力和快速的收敛性。-To better understand the genetic neural network contrast in the system, we control the indoor temperature, for example, set the room temperature control goal is 18 ℃ (20 ℃), other parameters remaining unchanged, respectively, according to a separate neural networks optimized based on genetic algorithm and neural network control simulation. The simulation results show that the genetic algorithm to optimize the neural network is very effective, through the use of genetic algorithms to optimize the neural network, it has a good generalization ability and fast convergence. Platform: |
Size: 19456 |
Author: |
Hits:
Description: 摘 要： 介绍BP算法神经网络由线拟舍方法，并借助MATLAB工具箱函数将它运用于方解石色散特性研
究，通过拟合效果图，误差曲线，误差范数反映BP神经网络的优越性，体现BP算法较高的预测能力和良好的泛化能
力，并且可以自动地确定数学模型．精确度高，原理也较简单，尤其对复杂的输入输出系统具有更好的效果。-Abstract： Curve fitting method of BP neural network was introduced and applied in the model of the dispersion of calcite
crystals by MATLAB tools．The results show that BP algorithm has high forecasting capacity and good generalization capacity
in three areas：the map of curve fitting，the deviation curve and the error norm．BP neural network can automatically identify
mathematical model，which has higher precision，and its principle is relatively simple．So it is a very good tool for complex
input-output system． Platform: |
Size: 293888 |
Author:zhenzhen |
Hits:
Description: 针对BP神经网络存在的缺点，本文利用遗传算法能够收敛到全局最优解而
且遗传算法鲁棒性强的特点将遗传算法同神经网络结合起来，不仅能发挥神经网
络的泛化映射能力，而且使神经网络具有很快的收敛性以及较强的学习能力。为
了验证遗传算法优化BP神经网络的有效性，本文将此算法应用到直线一级倒立
摆的稳定控制中，同时利用UbVIEW语言界面开发能力强，并且数据输入、网
络通信、硬件控制简单的优点，制作了倒立摆的仿真控制和实时控制软件。仿真
研究表明，遗传算法优化BP神经网络的控制器设计是可行的，可以很好的实现倒
立摆的稳定控制。
-BP neural network for the shortcomings, this paper genetic algorithm can converge to global optimal solution and
And genetic algorithm robustness characteristics of the genetic algorithm combined with neural networks, neural networks can not only play
The generalization ability of network mapping, and the neural network with fast convergence and a strong ability to learn. As
The validation of genetic algorithm to optimize the effectiveness of BP neural network, this algorithm is applied to this line a handstand
Put stability control, and interface development using UbVIEW language ability, and data entry, network
Network communications, hardware, the advantages of simple control, produced a simulation of the inverted pendulum control and real-time control software. Simulation
Studies have shown that genetic algorithm BP neural network controller design is feasible, can achieve a good fall
Li put stability control.
Platform: |
Size: 4796416 |
Author:高飞 |
Hits:
Description: 对量子粒子群优化(QPSO) 算法进行研究，提出了自适应量子粒子群优化(Adaptive QPSO) 算法，用于优化Elman 神经
网络的参数，改进了Elman 神经网络的泛化能力。利用网络流量时间序列数据进行预测，实验结果表明，采用AQPSO 算法优
化获得的Elman 神经网络模型不但具有较强的泛化能力，而且具有良好的稳定性，在网络流量时间序列数据的预测中具有
一定的实用价值-Quantum-behaved particle swarm optimization (QPSO) algorithm is researched and adaptive quantum-behaved particle
swarm optimization (AQPSO) algorithm is proposed in order to improve network’s performance. By applying AQPSO algorithm to
train the net parameters adopted in the Elman neural network, the generalization ability of the Elman neural network is improved. Experimental
results with network traffic time series data forecasting sets show that obtained network model has not only good generalization
properties, but also has better stability. It illustrates that Elman net with AQPSO optimization algorithm has the promising application
in network traffic time series data prediction. Platform: |
Size: 312320 |
Author:张杰 |
Hits:
Description: rbf神经网络应用于系统辨识,比BP网络具有较好的泛化能力,学习速度快,辨识效果好
在实际通信系统仿真过程中非常有用-RBF neural network is applied in system identification, than BP network has good generalization ability, learn fast, identify the effect is good
In the actual communication system simulation process is very useful Platform: |
Size: 1024 |
Author:tong |
Hits:
Description: ：根据公交站点客流集散量，选用合适的ＢＰ神经网络构建公交车辆调度形式的神经网络预报
模型．运用ＢＰ神经网络Ｍａｔｌａｂ工具箱设计的基本方法与过程，将ＢＰ网络模型引入公交车辆的调
度方案研究，计算结果表明，ＢＰ模型应用于公交车辆调度形式预测中具有较高的预测精度和良好
的泛化能力-according to the bus station passenger flow distribution quantity, choose suitable BP neural network construct public transport vehicle scheduling form of neural network prediction
Model. Using BP neural network Matlab toolbox basic design method and process, the BP network model of bus into the adjustment
Degree plan research, the calculation results show that the BP model is applied to public transport vehicle scheduling form prediction is of high precision and good
The generalization ability of the Platform: |
Size: 140288 |
Author:段建丽 |
Hits:
Description: 极限学习机（extreme learning machine）ELM是一种简单易用、有效的单隐层前馈神经网络SLFNs学习算法。2006年由南洋理工大学黄广斌副教授提出。传统的神经网络学习算法（如BP算法）需要人为设置大量的网络训练参数，并且很容易产生局部最优解。极限学习机只需要设置网络的隐层节点个数，在算法执行过程中不需要调整网络的输入权值以及隐元的偏置，并且产生唯一的最优解，因此具有学习速度快且泛化性能好的优点。-Extreme Learning Machine (extreme learning machine) ELM is an easy-to-use and effective single hidden layer feedforward neural network the SLFNs learning algorithm. 2006 by the Nanyang Technological University Associate Professor Huang Guangbin. Traditional neural network learning algorithm (BP) artificial network training parameters, and it is easy to generate a local optimal solution. Extreme Learning Machine network only need to set the number of hidden nodes, the algorithm implementation process does not need to adjust the network input weights and hidden element of bias, and only optimal solution, so the learning speed and generalization good performance advantages. Platform: |
Size: 691200 |
Author: |
Hits:
Description: NeC4.5: Neural Ensemble Based C4.5
Zhi-Hua Zhou, Member, IEEE, and Yuan Jiang
Abstract—Decision tree is with good comprehensibility while
neural network ensemble is with strong generalization ability. Platform: |
Size: 149504 |
Author:arsiphysic |
Hits:
Description: 极限学习机（extreme learning machine）ELM是一种简单易用、有效的单隐层前馈神经网络SLFNs学习算法。2004年由南洋理工大学黄广斌副教授提出。传统的神经网络学习算法（如BP算法）需要人为设置大量的网络训练参数，并且很容易产生局部最优解。极限学习机只需要设置网络的隐层节点个数，在算法执行过程中不需要调整网络的输入权值以及隐元的偏置，并且产生唯一的最优解，因此具有学习速度快且泛化性能好的优点。-ELM extreme learning machine (extreme learning machine) is a simple and easy to use, effective SLFNs single hidden layer feedforward neural network learning algorithm. Put forward by Huang Guangbin at nanyang technological university in 2004. The traditional neural network learning algorithm (BP algorithm) need to be set a large amount of network training parameter, and it s easy to produce the local optimal solution. Extreme learning machine only need to set the number of hidden layer nodes of networks, execution of the algorithm does not need to adjust the network weights of the input and hidden yuan bias, and produce the optimal solution, thus has advantages of fast learning speed and good generalization capability. Platform: |
Size: 15360 |
Author:jhon |
Hits:
Description: 几篇关于神经网络泛化的论文,几篇关于神经网络泛化的论文 不错的-A few paper on neural network generalization, a few good paper on neural network generalization Platform: |
Size: 636928 |
Author:seffcur |
Hits:
Search - good generalization neural network