Location:
Search - bp with fuzzy
Search list
Description: 论文标题:自适应模糊系统在手写体数字识别中的应用研究
作者:张镭
作者专业:计算机软件人工智能
导师姓名:黄战
授予学位:硕士
授予单位:暨南大学
授予学位时间:19990501
论文页数:59页
文摘语种:中文文摘
分类号:TP18 TP391.4
关键词:手写体数字 自适应 模糊逻辑 神经网络 模式识别
摘要:该文针对模式识别的特点,构造了适合于模式识别问题的自适应模糊系统,对三种不同学习算法加以改进,在手写全数字识别上对分类器进行了实现,并与采用BP算法训练的三层前馈神经网络分类器相比较,分析其优劣.仿真实验表明,在该文的样本集条件下,自适应模糊分类吕的识别性能优于神经网络分类器,这充分体现了自适应模糊技术用于数字识别的优越性和潜力.-thesis entitled : adaptive fuzzy system in a handwritten numeral recognition of applied research Author : Zhang Lei professional author : artificial intelligence computer software instructor Name : Huang war conferred degrees : Master award units : Jinan University conferred degrees : 19990501 page thesis : Abstracts 59 languages : Chinese Digest Key words : TP18-image Keywords : handwritten digital adaptive fuzzy logic neural network pattern recognition Abstract : In this paper the characteristics of pattern recognition, suitable for the construction of adaptive pattern recognition fuzzy systems, three different learning algorithm to improve the handwriting recognition on digital classification of the device to achieve, BP and with a three-tiered training algorithm for neural network clas
Platform: |
Size: 4194405 |
Author: 成东 |
Hits:
Description: 论文标题:自适应模糊系统在手写体数字识别中的应用研究
作者:张镭
作者专业:计算机软件人工智能
导师姓名:黄战
授予学位:硕士
授予单位:暨南大学
授予学位时间:19990501
论文页数:59页
文摘语种:中文文摘
分类号:TP18 TP391.4
关键词:手写体数字 自适应 模糊逻辑 神经网络 模式识别
摘要:该文针对模式识别的特点,构造了适合于模式识别问题的自适应模糊系统,对三种不同学习算法加以改进,在手写全数字识别上对分类器进行了实现,并与采用BP算法训练的三层前馈神经网络分类器相比较,分析其优劣.仿真实验表明,在该文的样本集条件下,自适应模糊分类吕的识别性能优于神经网络分类器,这充分体现了自适应模糊技术用于数字识别的优越性和潜力.-thesis entitled : adaptive fuzzy system in a handwritten numeral recognition of applied research Author : Zhang Lei professional author : artificial intelligence computer software instructor Name : Huang war conferred degrees : Master award units : Jinan University conferred degrees : 19990501 page thesis : Abstracts 59 languages : Chinese Digest Key words : TP18-image Keywords : handwritten digital adaptive fuzzy logic neural network pattern recognition Abstract : In this paper the characteristics of pattern recognition, suitable for the construction of adaptive pattern recognition fuzzy systems, three different learning algorithm to improve the handwriting recognition on digital classification of the device to achieve, BP and with a three-tiered training algorithm for neural network clas
Platform: |
Size: 4194304 |
Author: 成东 |
Hits:
Description: 一种基于模糊神经网络的控制策略，融合了模糊控制和神经网络的优点，根据变量的动态调整实施控制器的动态参数调整-Based on fuzzy neural network control strategy, the convergence of fuzzy control and neural network advantages, in accordance with the dynamic adjustment of the implementation of variable controller to adjust the dynamic parameters
Platform: |
Size: 232448 |
Author: 周炜 |
Hits:
Description: 用BP神经网络实现模糊控制规则为T=int[(e
+ec)/2]的模糊神经网络控制器。可以改变隐层节点数和学习速率。网络训练算法是变学习速率法。-BP neural network with fuzzy control rules for the T = int [(e+ Ec)/2] of the fuzzy neural network controller. Can change the hidden layer nodes and learning rate. Network training algorithm is a variable learning rate method.
Platform: |
Size: 4096 |
Author: 韩梅 |
Hits:
Description: 分类判别中，bayes判别的确具有明显的优势，与模糊，灰色，物元可拓相比，判别准确率一般都会高些，而BP神经网络由于调试麻烦，在调试过程中需要人工参与，而且存在明显的问题，局部极小点和精度与速度的矛盾，以及训练精度和仿真精度间的矛盾，等，尽管是非线性问题的一种重要方法，但是在我们项目中使用存在一定的局限，基于此，最近两天认真的研究了bayes判别，并写出bayes判别的matlab程序，与spss非逐步判别计算结果一致。-Classified Identifying, bayes discriminant does have a distinct advantage, with the fuzzy, gray, matter-element and extension compared to determine the exact rate will be higher in general, and the BP neural network trouble as a result of debugging, in the need to manually debug the process of participation, but also obvious problems, the local minimum point and the accuracy and speed of contradictions, as well as simulation training accuracy and precision of the conflict between, and so on, in spite of nonlinear problems is an important method, but the use of our project there are certain limitations, based on the Here, seriously the last couple of days to study the discriminant bayes and bayes discriminant of matlab to write procedures, and non-spss stepwise discriminant calculation results.
Platform: |
Size: 4096 |
Author: lili |
Hits:
Description: 为了提高三级倒立摆系统控制的响应速度和稳定性,在设计Mamdani 型模糊推理规则控制器控制倒立摆系统稳定的基础上,
设计了一种更有效率的基于Sugeno 型模糊推理规则的模糊神经网络控制器。该控制器使用BP 神经网络和最小二乘法的混
合算法进行参数训练,能够准确归纳输入输出量的模糊隶属度函数和模糊逻辑规则。通过与Mamdani 型控制器的仿真对比,
表明该Sugeno 型模糊神经网络控制器对三级倒立摆系统的控制具有良好的稳定性和快速性,以及较高的控制精度。-In order to improve the three-level control of inverted pendulum system response speed and stability, in the design of Mamdani-type fuzzy inference rules of the system controller to control the stability of inverted pendulum on the basis of a more efficient design based on Sugeno-type fuzzy inference rules of fuzzy neural network controller. The controller is the use of BP neural network and hybrid least squares training algorithm parameters can be accurately summed up the amount of input and output fuzzy membership function and fuzzy logic rules. Mamdani-type controller with a simulation comparison shows that the Sugeno-type fuzzy neural network controller for the three-tier control of inverted pendulum system with good stability and fast, as well as a higher control precision.
Platform: |
Size: 551936 |
Author: 月到风来AA |
Hits:
Description: 利用BP神经网络进行图像分割。主要适用于RGB信息丰富的图像。以RGB为BP网络的三个输入，与对应的灰度图对网络进行训练。-The use of BP neural network image segmentation. RGB is mainly applied to information-rich images. BP network to RGB for the three inputs, with grayscale corresponds to the network training.
Platform: |
Size: 24576 |
Author: 血狼 |
Hits:
Description: source code of train function of fuzzy bp neural network
Platform: |
Size: 1024 |
Author: z |
Hits:
Description: 利用支持向量机对T-S型模糊系统建模的方法，结合BP算法对参数进行优化，从一定程度上解决模糊系统建模所存在的模型结构复杂、维数灾、泛化能力不强和实时性差等问题。-this paper analyzed the approach that applied support vector machines to create novel model in the T-S fuzzy system, combined with BP algorithm which could optimize it, which, at some extent, eliminated the limitation during that process such as complexity of model construction, dimensionality curse, generalization ability poor and inaccurate immediateness.
Platform: |
Size: 1024 |
Author: 邓延丽 |
Hits:
Description: 这是关于神经网络图像识别方面的参考文献等等 希望对你有所帮助-These are some articles about BP nero-net to deal with pictures processing.i hope this will help in your study.
Platform: |
Size: 985088 |
Author: emilygenius |
Hits:
Description: Design a feedforward network is u
dehaze algorithms review
path planning using GA and ACO...
The neural network adaboost stron
TS neural network m files, fast c
bp neural network, written with C
Bayes net and memory based learni
Design a fuzzy control system to
This is a book about fuzzy system
Cloud adaptive genetic algorithm
BP neural network and RBF neural
use a three-layers BP network to
Professor Lin in Taiwan support v
neural network theory
Practical matlab time series ar m
efficient robot path planning-pub
A population-based artificial imm
A description of the neural netwo
Clustering AHC, K-means, SOM--Design a feedforward network is u
dehaze algorithms review
path planning using GA and ACO...
The neural network adaboost stron
TS neural network m files, fast c
bp neural network, written with C
Bayes net and memory based learni
Design a fuzzy control system to
This is a book about fuzzy system
Cloud adaptive genetic algorithm
BP neural network and RBF neural
use a three-layers BP network to
Professor Lin in Taiwan support v
neural network theory
Practical matlab time series ar m
efficient robot path planning-pub
A population-based artificial imm
A description of the neural netwo
Clustering AHC, K-means, SOM-NN
Platform: |
Size: 91136 |
Author: mohsen |
Hits:
Description: Design a feedforward network is u
dehaze algorithms review
path planning using GA and ACO...
The neural network adaboost stron
TS neural network m files, fast c
bp neural network, written with C
Bayes net and memory based learni
Design a fuzzy control system to
This is a book about fuzzy system
Cloud adaptive genetic algorithm
BP neural network and RBF neural
use a three-layers BP network to
Professor Lin in Taiwan support v
neural network theory
Practical matlab time series ar m
efficient robot path planning-pub
A population-based artificial imm
A description of the neural netwo
Clustering AHC, K-means, SOM--Design a feedforward network is u
dehaze algorithms review
path planning using GA and ACO...
The neural network adaboost stron
TS neural network m files, fast c
bp neural network, written with C
Bayes net and memory based learni
Design a fuzzy control system to
This is a book about fuzzy system
Cloud adaptive genetic algorithm
BP neural network and RBF neural
use a three-layers BP network to
Professor Lin in Taiwan support v
neural network theory
Practical matlab time series ar m
efficient robot path planning-pub
A population-based artificial imm
A description of the neural netwo
Clustering AHC, K-means, SOM-NN
Platform: |
Size: 13312 |
Author: mohsen |
Hits:
Description: 利用MATLAB软件，搭建一个GUI人工交互界面，分别用模糊控制、专家控制、BP神经网络控制实现PID控制在工程实践应用的性能比较！-Use MATLAB software, human interaction to build a GUI interface, respectively, with fuzzy control, expert control, BP neural network control to achieve PID control application performance engineering practice comparison!
Platform: |
Size: 22528 |
Author: 王茂正 |
Hits:
Description: The combination of Back Propagation Neural Network and Fuzzy Theory for Classification problem.
Platform: |
Size: 17408 |
Author: Cindywu_2015 |
Hits:
Description: 智能小车是移动机器人的一种，可通过计算机编程来实现其对行驶方向、启停以及速度的控制。要想让智能小车在行驶过程中能成功地避开障碍物，必须对其进行路径规划?，路径规划的任务是为小车规划一条从起始点到目标点的无碰路径。路径规划方法有：BP人工神经网络法（Back Propagation）、机器学习（Reinforcement Learning）、以及模糊控制（Fuzzy Control）方法等。模糊技术具有人类智能的模糊性和推理能力，在路径规划中，模糊推理的应用主要体现在基于行为的导航方式上，即将机器人的运动过程分解为避障、边界跟踪、调速、目标制导等基本行为，各基本行为的激活由不同的机构分别控制，机器人的最终操作由高层控制机构对基本行为进行平衡后作出综合反应。模糊控制方法将信息获取和模糊推理过程有机结合，其优点在于不依赖机器人的动力学、运动学模型，系统控制融入了人类经验，同时计算量小，构成方法较为简单，节省系统资源，实时性。本文探讨了模糊控制技术在避障路径规划中的应用，并对其进行了仿真设计。(There are many ways on autonomous mobile robot obstacle avoidance system
designing, which based on fuzzy control of robot obstacle avoidance system is to use the fuzzy logic control system to determine the environmental information around the robot, then plan out a route to the target point with collision-free path. This method has a small footprint, responsive and could be able to cope with relatively complex external environment. In this paper, the main content is fuzzy control theory based obstacle avoidance of mobile robot path planning by research.)
Platform: |
Size: 222208 |
Author: zallen
|
Hits:
Description: 智能小车是移动机器人的一种，可通过计算机编程来实现其对行驶方向、启停以及速度的控制。要想让智能小车在行驶过程中能成功地避开障碍物，必须对其进行路径规划?，路径规划的任务是为小车规划一条从起始点到目标点的无碰路径。路径规划方法有：BP人工神经网络法（Back Propagation）、机器学习（Reinforcement Learning）、以及模糊控制（Fuzzy Control）方法等。(There are many ways on autonomous mobile robot obstacle avoidance system
designing, which based on fuzzy control of robot obstacle avoidance system is to use the fuzzy logic control system to determine the environmental information around the robot, then plan out a route to the target point with collision-free path. This method has a small footprint, responsive and could be able to cope with relatively complex external environment. In this paper, the main content is fuzzy control theory based obstacle avoidance of mobile robot path planning by research.)
Platform: |
Size: 444416 |
Author: zallen
|
Hits:
Description: 根据所学过的BP网络设计及改进方案设计实现模糊控制规则为T = int((e+ec)/2)的模糊神经网络控制器，其中输入变量e和ec的变化范围分别是：e = int[-2, 2]，ec = int[-2, 2]。网络设计的目标误差为 0.001。(According to the BP network design and improvement plan that we have learned, we design a fuzzy neural network controller with fuzzy control rule T = int ((e+ec) /2). The input variables E and EC vary from e = int[-2, 2], EC = int[-2, 2]. The target error of network design is 0.001.)
Platform: |
Size: 11264 |
Author: 杰洛
|
Hits:
Description: 实现控制规则为T=int（(e+e1)/2）的模糊神经网络控制器(A fuzzy neural network controller with T=int ((e+e1) /2) control rule is implemented.)
Platform: |
Size: 1024 |
Author: 随lab |
Hits: