In this demo, I use the EM algorithm with a Rauch-Tung-Striebel smoother and an M step, which I ve recently derived, to train a two-layer perceptron, so as to classify medical data (kindly provided by Steve Roberts and Will Penny from EE, Imperial College). The data and simulations are described in: Nando de Freitas, Mahesan Niranjan and Andrew Gee Nonlinear State Space Estimation with Neural Networks and the EM algorithm After downloading the file, type "tar -xf EMdemo.tar" to uncompress it. This creates the directory EMdemo containing the required m files. Go to this directory, load matlab5 and type "EMtremor". The figures will then show you the simulation results, including ROC curves, likelihood plots, decision boundaries with error bars, etc. WARNING: Do make sure that you monitor the log-likelihood and check that it is increasing. Due to numerical errors, it might show glitches for some data sets.
标签： Rauch-Tung-Striebel algorithm smoother which
上传时间： 2016-04-15
上传用户：zhenyushaw
Special picture button, easy configure... release. You only need one picture for pressed and one for normal state.
上传时间： 2014-08-26
上传用户：c12228
EKF-SLAM Simulator This version of the simulator uses global variables for all large objects, such as the state covariance matrix. While bad programming practice, it is a necessary evil for MatLab efficiency, as MatLab has no facility to avoid gratuitous memory allocation and copying when passing (and modifying) variables between functions. With this concession, effort has been made to keep the code as clean and modular as possible.
标签： Simulator simulator variables EKF-SLAM
上传时间： 2016-05-02
上传用户：lunshaomo
aiNet application is a very powerful and a very simple tool for solving the problems which are usually solved with artificial neural networks (ANN). All possible tests we had run proved that the results obtained with aiNet are at least as good as the results obtained with some other ANNs. Let us state some of aiNet抯 features. (c) aiNet 1995-1997
标签： very application powerful problems
上传时间： 2014-01-16
上传用户：wang5829
Ants performing 3 actions: searching ore , mining ore , returning ore basic Artificial Neurological Network working the learning proces to pick their state through Genetic Programming 人工智能中的蚁群算法
标签： ore Neurological performing Artificial
上传时间： 2013-12-26
上传用户：hongmo
这是一个非常简单的遗传算法源代码，是由Denis Cormier (North Carolina State University)开发的，Sita S.Raghavan (University of North Carolina at Charlotte)修正。代码保证尽可能少，实际上也不必查错。对一特定的应用修正此代码，用户只需改变常数的定义并且定义“评价函数”即可。注意代码 的设计是求最大值，其中的目标函数只能取正值；且函数值和个体的适应值之间没有区别。该系统使用比率选择、精华模型、单点杂交和均匀变异。如果用 Gaussian变异替换均匀变异，可能得到更好的效果。代码没有任何图形，甚至也没有屏幕输出，主要是保证在平台之间的高可移植性。
上传时间： 2013-12-05
上传用户：lili123
GNU ccScript is a C++ class framework for creating a virtual machine execution system for use with and as a scripting/assembler language for state-transition driven realtime systems. The most common example of this is as the core of the scripting engine found in GNU Bayonne.
标签： framework for execution ccScript
上传时间： 2013-12-18
上传用户：sssl
SOPC实验--Hello World实验:启动Quartus II软件，选择File→New Project Wizard，在出现的对话框中填写项目名称 2、 点击Finish，然后选择“是”。选择Assignments→Device，改写各项内容。Family改为CycloneII，根据实验板上的器件选择相应的器件，本实验选择EP2C5T144C8,点击对话框中的Device & Pin Options，在Configuration中，选项Use Configuration Device为EPCS1，选项Unused Pins为As inputs,tri-stated.
上传时间： 2014-01-13
上传用户：梧桐
The MEASURE program uses analog and digital inputs to simulate a datalogger. You may watch the value of analog input POT1 and the state of S2, S3 Buttons on MCBSTM32 evaluation board.
标签： datalogger simulate MEASURE program
上传时间： 2016-07-17
上传用户：qq21508895
Zero-order-hold Intended for a senior-level course on the analysis and design of digital control systems, the text is also useful for graduate students and practicing engineers who are learning state-space design techniques.
标签： Zero-order-hold senior-level Intended analysis
上传时间： 2013-12-04
上传用户：liuchee
