Description Usage Arguments Value Examples
Training by using nerual network with gradient descending (real numbers for regression, probabilities for binary classification).
1 2 | NNetIterations(X.mat, y.vec, max.iterations, step.size, n.hidden.units,
is.train)
|
X.mat |
(feature matrix, n_observations x n_features) |
y.vec |
(label vector, n_observations x 1) |
max.iterations |
(int scalar > 1) |
n.hidden.units |
(number of hidden units) |
is.train |
(logical vector of size n_observations, TRUE if the observation is in the train set, FALSE for the validation set) |
pred.mat (n_observations x max.iterations matrix of predicted values or n x k)
W.mat:final weight matrix(n_features+1 x n.hidden.units or p+1 x u)
v.vec: final weight vector (n.hidden.units+1 or u+1).
predict(testX.mat): a function that takes a test features matrix and returns a vector of predictions (real numbers for regression, probabilities for binary classification) The first row of W.mat should be the intercept terms; the first element of v.vec should be the intercept term.
1 2 3 4 5 6 7 8 9 | data(ozone, package = "ElemStatLearn")
y.vec <- ozone[, 1]
X.mat <- as.matrix(ozone[,-1])
num.train <- dim(X.mat)[1]
num.feature <- dim(X.mat)[2]
X.mean.vec <- colMeans(X.mat)
X.std.vec <- sqrt(rowSums((t(X.mat) - X.mean.vec) ^ 2) / num.train)
X.std.mat <- diag(num.feature) * (1 / X.std.vec)
X.scaled.mat <- t((t(X.mat) - X.mean.vec) / X.std.vec)
|
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.