jboss 開發人員 手冊
JBoss: A Developer s Notebook also introduces the management console, the web services messaging features, enhanced monitoring capabilities, and shows you how to improve performance. At the end of each lab, you ll find a section called "What about..." that anticipates and answers likely follow-up questions, along with a section that Points you to articles and other resources if you need more information.
This program demonstrates some function approximation capabilities of a Radial Basis Function Network.
The user supplies a set of training Points which represent some "sample" Points for some arbitrary curve. Next, the user specifies the number of equally spaced gaussian centers and the variance for the network. Using the training samples, the weights multiplying each of the gaussian basis functions arecalculated using the pseudo-inverse (yielding the minimum least-squares solution). The resulting network is then used to approximate the function between the given "sample" Points.
The EM algorithm is short for Expectation-Maximization algorithm. It is based on an iterative optimization of the centers and widths of the kernels. The aim is to optimize the likelihood that the given data Points are generated by a mixture of Gaussians. The numbers next to the Gaussians give the relative importance (amplitude) of each component.
This is SvmFu, a package for training and testing support vector
machines (SVMs). It s written in C++. It uses templates. The
advantage of templates is that the types of kernel values and data
Points can be varied to suit the problem.
PIECEWISE_EVAL: evaluates a piecewise function of x
usage: y = PIECEWISE_EVAL(x,breakPoints,funs)
arguments (input)
x - vector or array of Points to evaluate though the function
breakPoints - list of n breakPoints, -inf and +inf are implicitly
/*
* EULER S ALGORITHM 5.1
*
* TO APPROXIMATE THE SOLUTION OF THE INITIAL VALUE PROBLEM:
* Y = F(T,Y), A<=T<=B, Y(A) = ALPHA,
* AT N+1 EQUALLY SPACED Points IN THE INTERVAL [A,B].
*
* INPUT: ENDPoints A,B INITIAL CONDITION ALPHA INTEGER N.
*
* OUTPUT: APPROXIMATION W TO Y AT THE (N+1) VALUES OF T.
*/
support vector classification machine
％ soft margin
％ uses "kernel.m"
％
％ xtrain: (Ltrain,N) with Ltrain: number of Points N: dimension
％ ytrain: (Ltrain,1) containing class labels (-1 or +1)
％ xrun: (Lrun,N) with Lrun: number of Points N: dimension
％ atrain: alpha coefficients (from svcm_train on xtrain and ytrain)
％ btrain: offest coefficient (from svcm_train on xtrain and ytrain)
％
％ ypred: predicted y (Lrun,1) containing class labels (-1 or +1)
％ margin: (signed) separation from the separating hyperplane (Lrun,1
One-channel queuing system simulator (M/M/1)
* Arrival and service times are random and distributed exponetially.
*
* The simulator is time-slice-driven, i.e. the system model is being
* run at discrete time Points, with constant increments deltaT.
* At each such time moment, program checks if a new item arrival or
* release has occurred during previus deltaT.
This paper addresses a stochastic-#ow network in which each arc or node has several capacities and may
fail. Given the demand d, we try to evaluate the system reliability that the maximum #ow of the network is
not less than d. A simple algorithm is proposed "rstly to generate all lower boundary Points for d, and then
the system reliability can be calculated in terms of such Points. One computer example is shown to illustrate
the solution procedure.
