library(RSNNS)

# function compute accuracy
# input: 
#	model: list(weights, bias)
#	x: a n*d matrix in which each row is a datum point
#	y: a n*1 matrix in which each row is the target of x[i,]
# output: classification error
compute.accuracy <- function(model, x, y) {
	n.cases <- dim(x)[1]
	pred <- (predict(model, x) > 0.5) * 1.
	acc	<- sum((y == pred)*1.)/n.cases
	return(acc)
}

#############################################################

maxit = 100
learn.rate = 0.1
size = c(5)

x <- t(matrix(c(
				0,0,
				0,1,
				1,0,
				1,1),
		2,4))

y <- matrix(c(
				0,
				1,
				1,
				1), 
		4, 1)

colnames(x) <- c("x1", "x2")
model <- mlp(x, y, size=size, maxit = maxit, learnFuncParams = learn.rate)
	
# report result
plotIterativeError(model)
cat("accuracy: ", compute.accuracy(model, x, y), "\n")