Description: 人工神经网络识别，人工智能实验课上做的人工神经网络识别，人工智能实验课上做的-Artificial neural network identification, Artificial Intelligence class to do the experiment of artificial neural networks, artificial intelligence to do the experimental class Platform: |
Size: 7448576 |
Author:庄重 |
Hits:
Description: PNN又称为概率神经网络,它最初由数学家Specht于1990年提出,后经Master[1995]等不断发展和完善,已成功地应用于机器学习、人工智能、自动控制等众多领域.概率神经网络比多层前馈网络的数学原理简单,且易于实现-PNN is also known as the probabilistic neural network, which was first introduced by the mathematician Specht in 1990, after the Master [1995], such as the continuous development and improvement has been successfully applied to machine learning, artificial intelligence, automatic control and many other fields. Probabilistic neural network than the multi-layer feedforward network of simple math, and are easy to achieve Platform: |
Size: 8192 |
Author:piano |
Hits:
Description: 人工神经网络(ANN)的泛化特性是神经网络最重要的特性,同时也是最不容易保证的特性。本程序对改进泛化的神经网络算法以及新兴的机器学习算法——支持向量机算法进行研究,-Artificial Neural Network (ANN) the generalization characteristics of neural networks are the most important characteristics, but also not easy to guarantee the most features. This procedure for improving the generalization of neural network algorithm, as well as the emerging machine learning algorithms- Support Vector Machine algorithm research, Platform: |
Size: 7168 |
Author:王旭 |
Hits:
Description: 一种简单有效的基于动态时变语音识别源码
对于大多数研究者来说,寻找能够匹配二重时间序列信号的最佳途径是很重要的,因为它有许多重要的应用需求.DTW是实现这项工作的显著技术,尤其在语音识别技术领域,在这里一个测试信号被按照参照模板拉伸或压缩,
-Searching for the best path that matches two time-series signals is the main task for many researchers, because of its importance in these applications. Dynamic Time-Warping (DTW) is one of the prominent techniques to accomplish this task, especially in speech recognition systems. DTW is a cost minimisation matching technique, in which a test signal is stretched or compressed according to a reference template.
Although there are other advanced techniques in speech recognition such as the hidden Markov modelling (HMM) and artificial neural network (ANN) techniques, the DTW is widely used in the small-scale embedded-speech recognition systems such as those embedded in cell phones. The reason for this is owing to the simplicity of the hardware implementation of the DTW engine, which makes it suitable for many mobile devices. Additionally, the training procedure in DTW is very simple and fast, as compared with the HMM and ANN rivals.
Platform: |
Size: 2658304 |
Author:宋小小 |
Hits:
Description: 运用人工神经网络技术预测风速，主要介绍了神经网络的实现方法，以及预测结果的比较-The use of artificial neural network technology forecasting wind speed, mainly the realization of a neural network method and the comparison of predicted results Platform: |
Size: 189440 |
Author:沈燕 |
Hits:
Description: 倒立摆是一种复杂、时变、非线性、强耦合、自然不稳定的高阶系统，许多抽象的控制理论概念都可以通过倒立摆实验直观的表现出来。基于人工神经网络BP算法的倒立摆小车实验仿真训练模型，其倒立摆BP网络为4输入3层结构。输入层分别为小车的位移和速度、摆杆偏离铅垂线的角度和角速度。隐含层单元数16个。输出层设置为1个输出单元。输入层采用Tansig函数，隐含层采用Logsig函数，输出层采用Purelin函数。用Matlab 6.5数值计算软件对模型进行学习训练，并与线性反馈控制逻辑算法对比，表明倒立摆控制BP算法精度高、收敛快，在非线性控制、鲁棒控制等领域具有良好的应用前景。 -Inverted pendulum is a complex, time-varying, nonlinear, strong coupling, the natural instability of the high-end systems, many of the abstract concept of control theory to pass through the inverted pendulum experiment demonstrated intuitive. Based on artificial neural network BP algorithm inverted pendulum experiment simulation training model car, the Inverted Pendulum BP network input 3-layer structure of 4. Input layer, respectively, for the car s displacement and speed of deviation from the plumb line placed under the angle and angular velocity. Hidden layer unit number 16. Output layer is set to an output unit. Tansig function using input layer, hidden layer Logsig function used, the output layer Purelin function. Numerical calculation using Matlab 6.5 software for learning and training model, and linear feedback control logic algorithm comparison, show that the inverted pendulum control of BP algorithm and high precision, fast convergence in nonlinear control, robust control and Platform: |
Size: 217088 |
Author:月到风来AA |
Hits:
Description: Fast Artificial Neural Network Library是一个免费开源的神经网络库，它用C实现了支持全连接及稀连接的多层人工神经网络，并且支持定点和浮点数的跨平台运行。库中包含有易于处理训练数据的框架。它易于使用、通用、文档完备并且快速。目前已有PHP, C++, .NET, Ada, Python, Delphi, Octave, Ruby, Prolog Pure Data 和 Mathematica的绑定。库中还附有一本带例子和关于如何使用本库的建议的参考手册，本库也有一个可用的图形用户接口。-Fast Artificial Neural Network Library is a free open source neural network library, it uses C to achieve full connectivity and dilute support for multi-layer artificial neural network connections, and supports fixed and floating-point cross-platform operation. Library contains easy to handle training data framework. It is easy to use, universal, comprehensive documentation and quick. At present, PHP, C++,. NET, Ada, Python, Delphi, Octave, Ruby, Prolog Pure Data and Mathematica bindings. The library is accompanied with an example of how to use the library and on the recommendations of the reference manual, available in this library also has a graphical user interface. Platform: |
Size: 4033536 |
Author:hopper |
Hits:
Description: 利用MATLAB构建的三层人工神经网络，网络结构清楚，具有一定参考价值-The use of MATLAB built three artificial neural network, the network structure is clear and has a certain reference value Platform: |
Size: 13312 |
Author:zhangxi |
Hits:
Description: 火灾视觉特征的提取是视觉火灾探测中的关键问题. 我们主要研究色彩、纹理以及轮廓脉动
等特征的提取,并提出一种度量轮廓脉动信息的距离模型,该模型在规格化的傅立叶描述子空间能
够准确地度量这种时空闪烁特征. 实验结果表明,该方法具有比较好的鲁棒性,有助于提高视觉火
灾探测的准确率、降低误报漏报率.-Based on investigating color , text ure and temporal feat ures for vision based fire detection , a
distance model of contour fluct uation between two successive f rames in t he normalized Fourier descriptor s
domain was presented to measure t his time varying contour fluct uation feat ure of flame. The model of
contour fluct uation is effective and robust for fire recognition. To f urt her reduce fal se alarms , several
features ext racted according to color , text ure and the distance model were toget her regarded as a joint
feature vector for artificial neural network to detect fire. Experiment s show t hat the algorithm is effective
and robust , and t hat it is significant for improving accuracy and reducing fal se alarms. Platform: |
Size: 819200 |
Author:陈卿 |
Hits:
Description: 人工神经网络
北京工业大学计算机学院
作为人工神经网络的入门教程，用于将学生引入人工神经网络及其应用的研究领域-Artificial Neural Networks Computer Science, Beijing University of artificial neural network entry as a tutorial for the students of artificial neural network and its application field of study Platform: |
Size: 600064 |
Author:viet |
Hits:
Description: 人工神经网络用Sanger算法求解多个模式的主分量问题。-Sanger method using artificial neural network model for solving the main component of many problems. Platform: |
Size: 1024 |
Author:萧茅律 |
Hits:
Description: 数据挖掘和知识发现（Data Mining and Knowledge Discovery，DMKD）技术就是在这样的背景下产生的，是在数据库技术、机器学习、人工智能、统计分析、模型逻辑、人工神经网络和专家系统等基础上发展起来的新兴交叉科学，是继网络之后的又一个技术热点。如果将数据库中的大量数据比喻为矿床，则DMKD技术就是从这矿床中挖掘知识的“金块”的工具。由于其诱人的前景和巨大的难道，使得DMKD成为计算机信息处理领域的研究热点和前沿技术。-Data Mining and Knowledge Discovery (Data Mining and Knowledge Discovery, DMKD) technology is produced in this background is in database technology, machine learning, artificial intelligence, statistical analysis, model logic, artificial neural network and expert system based on developed new interdisciplinary science, is the second network technology hot spot after another. If the database of a large number of data compared to deposits, the DMKD technology is the knowledge of mining this deposit, the "gold" tool. Because of its attractive prospects and huge Could make DMKD a computer information processing in the field of research focus and cutting-edge technology Platform: |
Size: 7132160 |
Author:kizo |
Hits:
Description: 《数字图像处理与机器视觉:Visual C++与Matlab实现》4
特征提取,图像识别初步,人工神经网络,基于ANN的数字字符识别系统-" Digital image processing and machine vision: Visual C++ and Matlab to achieve" four feature extraction, image recognition initially, artificial neural network, ANN based digital character recognition system Platform: |
Size: 726016 |
Author:陈新秋 |
Hits:
Description: Image Compression using Artificial Neural Networks
This code is developed in MATLAB 6.5 and can used in Windows platform. Program contain all necessary files. For training the network use Train.m and Codec.m compress images by trained network. Platform: |
Size: 180224 |
Author:Aso |
Hits:
Search - artificial neural network