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
1) Write a function reverse(A) which takes a matrix A of arbitrary dimensions as input and returns a matrix B consisting of the columns of A in reverse order. Thus for example, if A = 1 2 3 then B = 3 2 1 4 5 6 6 5 4 7 8 9 9 8 7 Write a main program to call reverse(A) for the matrix A = magic(5). Print to the screen both A and reverse(A). 2) Write a program which accepts an input k from the keyboard, and which prints out the smallest fibonacci number that is at least as large as k. The program should also print out its position in the fibonacci sequence. Here is a sample of input and output: Enter k>0: 100 144 is the smallest fibonacci number greater than or equal to 100. It is the 12th fibonacci number.
标签： dimensions arbitrary function reverse
上传时间： 2016-04-16
上传用户：waitingfy
This demo nstrates how to use the sequential Monte Carlo algorithm with reversible jump MCMC steps to perform model selection in neural networks. We treat both the model dimension (number of neurons) and model parameters as unknowns. The derivation and details are presented in: Christophe Andrieu, Nando de Freitas and Arnaud Doucet. Sequential Bayesian Estimation and Model Selection Applied to Neural Networks . Technical report CUED/F-INFENG/TR 341, Cambridge University Department of Engineering, June 1999. After downloading the file, type "tar -xf version2.tar" to uncompress it. This creates the directory version2 containing the required m files. Go to this directory, load matlab5 and type "smcdemo1". In the header of the demo file, one can select to monitor the simulation progress (with par.doPlot=1) and modify the simulation parameters.
标签： sequential reversible algorithm nstrates
上传时间： 2014-01-18
上传用户：康郎
The algorithms are coded in a way that makes it trivial to apply them to other problems. Several generic routines for resampling are provided. The derivation and details are presented in: Rudolph van der Merwe, Arnaud Doucet, Nando de Freitas and Eric Wan. The Unscented Particle Filter. Technical report CUED/F-INFENG/TR 380, Cambridge University Department of Engineering, May 2000. After downloading the file, type "tar -xf upf_demos.tar" to uncompress it. This creates the directory webalgorithm containing the required m files. Go to this directory, load matlab5 and type "demo_MC" for the demo.
标签： algorithms problems Several trivial
上传时间： 2014-01-20
上传用户：royzhangsz
Copy gen_jmsn.dll to your Winamp Plugins Directory. JMSN Auto Nickname Changer plugins support only winamp 2.x version. [StartUp] In Tools -> Options.. -> Auto Nickname tabs, Configure your prefix and postfix besides your mp3 name And Press Start Button. so nickname changer listener will be started. [Configure] If I m listening Marilyn Manson - This Is The New Shit , Prefix : Jang-Ho Hwang listen Postfix: ~* When winamp song was changed, your nickname will be Jang-Ho Hwang listen Marylyn Manson - This Is The New Shit~* [Winamp plugin configure] In Winamp 2.x, Press Control+P (Preferences). You will find JMSN Nickname Changer Plug-In v0.7 in Plug-ins -> General purpose. Click Configure and set access password. it will keep your nickname. Enjoy it
标签： Directory gen_jmsn Nickname Changer
上传时间： 2014-01-20
上传用户：zhuimenghuadie
SMT365 has 1MBytes of internal memory to store program and fast access buffers (0x00000 -> 0xFFFFF). To display data captured, use Test.m (MATLAB application)
标签： internal 1MBytes 0x00000 buffers
上传时间： 2016-04-24
上传用户：924484786
Implement the following integer methods: a) Method celsius returns the Celsius equivalent of a Fahrenheit calculation celsius = 5.0 / 9.0 * ( fahrenheit - 32 ) b) Method fahrenheit returns the Fahrenheit equivalent of a Celsius the calculation fahrenheit = 9.0 / 5.0 * celsius + 32 c) Use the methods from parts (a) and (b) to write an application either to enter a Fahrenheit temperature and display the Celsius or to enter a Celsius temperature and display the Fahrenheit equivalent.
标签： equivalent Implement the following
上传时间： 2014-01-19
上传用户：jackgao
The MDP toolbox proposes functions related to the resolution of discrete-time Markov Decision Process : finite horizon, value iteration, policy iteration, linear programming algorithms with some variants. The functions (m-functions) were developped with MATLAB v6.0 (one of the functions requires the Mathworks Optimization Toolbox) by the decision team of the Biometry and Artificial Intelligence Unit of INRA Toulouse (France). The version 2.0 (February 2005) handles sparse matrices and contains an example
标签： discrete-time resolution functions Decision
上传时间： 2014-01-01
上传用户：xuanjie
This LDPC software is intended as an introduction to LDPC codes computer based simulation. The pseudo-random irregular low density parity check matrix is based on Radford M. Neal’s programs collection, which can be found in [1]. While Neal’s collection is well documented, in my opinion, C source codes are still overwhelming, especially if you are not knowledgeable in C language. My software is written for MATLAB, which is more readable than C. You may also want to refer to another MATLAB based LDPC source codes in [2], which has different flavor of code-writing style (in fact Arun has error in his log-likelihood decoder).
标签： LDPC introduction simulation software
上传时间： 2014-01-14
上传用户：大融融rr
There are two files in the zip folder. bpsk_spread.m and jakesmodel.m Steps for simulation: 1] Run jakesmodel.m first 2] Then run bpsk_spread.m . 3] Note that during the first run bpsk_spread.m has no rayleigh fading.This is because the corresponding code has been commented 4] The resulting performance is stored in BER_awgn. 5] Now uncomment the Rayleigh Fading code in bpsk_spread.m file. 6] Same time comment BER_awgn (line 112) and uncomment BER_ray variable. 7] Run the simulation. To compare the perfromances of the receiver using DSSS plot the BER_awgn and BER_ray
标签： bpsk_spread jakesmodel simulation folder
上传时间： 2016-05-19
上传用户：ynsnjs
