Implementation of Collobert, R., Bengio, S., and Bengio, Y. "A parallel mixture of SVMs for very large scale problems. Neural computation".
1 2 3 
x 
the nxp training data matrix. Could be a matrix or an object that can be transformed into a matrix object. 
y 
a response vector for prediction tasks with one value for each of the n rows of 
m 
the number of experts 
c 
a positive constant controlling the upper bound of the number of samples in each subset. 
max.iter 
the number of iterations 
hidden 
the number of neurons on the hidden layer 
learningrate 
the learningrate for the back propagation 
threshold 
neural network stops training once all gradient is below the threshold 
stepmax 
the maximum iteration of the neural network training process 
seed 
the random seed. Set it to 
valid.x 
the mxp validation data matrix. 
valid.y 
if provided, it will be used to calculate the validation score with 
valid.metric 
the metric function for the validation result. By default it is the accuracy for classification. Customized metric is acceptable. 
verbose 
a logical value indicating whether to print information of training. 
... 
other parameters passing to 
expert
a list of svm experts
gater
the trained neural network model
valid.pred
the validation prediction
valid.score
the validation score
valid.metric
the validation metric
time
a list object recording the time consumption for each steps.
1 2 3 4 5 6 7 8  data(svmguide1)
svmguide1.t = as.matrix(svmguide1[[2]])
svmguide1 = as.matrix(svmguide1[[1]])
gaterSVM.model = gaterSVM(x = svmguide1[,1], y = svmguide1[,1], hidden = 10, seed = 0,
m = 10, max.iter = 1, learningrate = 0.01, threshold = 1, stepmax = 100,
valid.x = svmguide1.t[,1], valid.y = svmguide1.t[,1], verbose = FALSE)
table(gaterSVM.model$valid.pred,svmguide1.t[,1])
gaterSVM.model$valid.score

Questions? Problems? Suggestions? Tweet to @rdrrHQ or email at ian@mutexlabs.com.
All documentation is copyright its authors; we didn't write any of that.